לוח משרות דרושים חוקר בינה מלאכותית, לחיפוש זה נמצאו 34 משרות

we are looking for a Lead Endpoint Researcher.
What You'll Do
Research AI coding agent runtimes, reverse-engineer how tools such as Claude Code, Cursor, Copilot CLI, Codex, and emerging agents execute commands, access files, spawn processes, and interact with the operating system.
Design agent sandboxing architectures that safely constrain filesystem access, networking, process execution, credentials, and other sensitive endpoint capabilities.
Explore and implement OS-native isolation mechanisms across macOS, Windows, and Linux, including containers, namespaces, sandbox profiles, virtualization, restricted processes, and permission models.
Build endpoint "harnesses" that allow TokenShift to intercept, control, observe, and modify agent execution flows.
Design infrastructure for deploying and running local LLMs across heterogeneous endpoint fleets, accounting for operating system, CPU architecture, GPU availability, memory constraints, and hardware acceleration.
Evaluate local inference runtimes and model formats such as llama.cpp, MLX, ONNX Runtime, Ollama, vLLM-compatible runtimes, and emerging alternatives.
Develop mechanisms for model discovery, installation, versioning, updates, health monitoring, and lifecycle management across large numbers of developer machines.
Research hardware-aware model selection and routing, deciding which models can run effectively on Apple Silicon, NVIDIA GPUs, Windows workstations, Linux machines, CPU-only environments, and other endpoint configurations.
Build benchmarks that measure model latency, throughput, memory consumption, startup time, resource contention, and developer experience on real endpoint hardware.
Investigate security boundaries between local models, cloud-hosted models, agents, MCP servers, shells, and enterprise resources.
Collaborate with the core CLI and platform teams to take endpoint research from prototype through production.
Track the rapidly evolving AI agent, sandboxing, and local inference ecosystems and proactively identify technologies should support.

We are seeking a Senior AI Researcher to lead post-training evaluation, red-teaming, and reinforcement learning (RL) gym audits on open-weight models. The ideal candidate will establish rigorous benchmarking methodologies, evaluate large language models (LLMs) against complex threats like Indirect Prompt Injections (IPI), and construct post-training evaluation pipelines that accurately measure realistic frontier-level security capabilities.
Key Responsibilities
RL Post-Training & Benchmarking
Execute post-training runs (e.g. GRPO) using mainstream open-weight generalist models against security-focused RL environments, targeting threat vectors like Indirect Prompt Injection (IPI).
Reward Diagnostics & Trace Analysis - Analyze live loss curves and rollout traces to identify reward hacking, lazy policy convergence, and flawed or over/under-specified verifiers.
Task & Environment Auditing
Review tasks and multi-turn environments (including tool use, web navigation, and computer use) for realism, threat model accuracy, data distribution, and dataset balance.
Performance Reporting (Gym Cards)
Generate comprehensive evaluation cards detailing hill-climbing performance uplift across checkpoints, failure modes, tokens/turns per rollout, and task-level success rates.
Integration & Orchestration
Integrate dockerized environments (e.g., Harbor format) into internal training frameworks, optimizing reset/statefulness semantics, concurrency, and throughput ceilings.

we are a leading trust, safety, and security company. Just like Alice herself, we go down the rabbit hole into the emerging world of AI and focus on safeguarding these technologies. In a world where AI has fundamentally changed the nature of risk, our company offers coverage across the entire AI lifecycle. We're currently on the ground floor of an exciting new initiative: building an "Elite Collective" of the world's premier cyber specialists-high-stakes, project-based work for the "best of the best" red-teamers in the industry. Work is on-demand and project-dependent, scaling up and down based on the needs of the client. This is not a high-volume, repetitive role; it is an opportunity to be tapped for specific, high-impact interventions when your unique expertise is required. The most sophisticated technology challenges in the world are waiting down the rabbit hole. Were looking for the sharpest minds to help us secure the frontier. The invitation is open: Come join us at the tea party. About the position: As one of our companys Security Red Team Specialists, youll focus on Generative AI Models. You will play a critical role in enhancing the security and integrity of our cutting-edge AI technologies. Your primary responsibility will be to conduct analysis and testing of our generative AI systems, including but not limited to language models, image generation models, and any related infrastructure. Your objective is to help clients secure their AI models and frameworks by identifying weaknesses, assessing risks, and providing clear steps for improvement. Key Responsibilities
* Simulated Cyber Attacks: Conduct sophisticated and comprehensive simulated attacks on generative AI models and their operating environments to uncover vulnerabilities.
* Vulnerability Assessment: Evaluate the security posture of AI models and infrastructure, identifying weaknesses and potential threats.
* Risk Analysis: Perform thorough risk analysis to determine the impact of identified vulnerabilities and prioritize mitigation efforts.
* Mitigation Strategies: Collaborate with development and security teams to develop effective strategies to mitigate identified risks and enhance model resilience.
* Research and Innovation: Stay abreast of the latest trends and developments in AI security, ethical hacking, and cyber threats. Apply innovative testing methodologies to ensure cutting-edge security practices.
* Documentation and Reporting: Maintain detailed documentation of all red team activities, findings, and recommendations. Prepare and present reports to senior management and relevant stakeholders.
About us:
we are a trust, safety, and security company built for the AI era. We safeguard the communicative technologies people use to create, collaborate, and interact- whether with each other or with machines. In a world where AI has fundamentally changed the nature of risk, our company provides end-to-end coverage across the entire AI lifecycle. We support frontier model labs, enterprises, and UGC platforms with a comprehensive suite of solutions: from model hardening evaluations and pre-deployment red-teaming to runtime guardrails and ongoing drift detection. we are widely considered a global leader in online safety and AI security. We have some of the most forward-thinking and passionate minds in the world working to safeguard over 3 billion users across the largest AI and tech platforms. If you're creative and driven to secure the future of AI, we want to hear from you!

We're looking for an Experienced Performance Researcher to join our founding team. Youll be responsible for building and optimizing scalable cloud infrastructure solutions tailored for AI workloads. This role offers a unique opportunity to directly shape our infrastructure strategy, improve system reliability and performance, and contribute to establishing us as a leader in adaptive AI compute management.
Join us to tackle the magic that make AI tick under the hood and build the backbone powering the AI revolution.
What Youll Do
- Design and build high-performance distributed inference pipelines for LLMs, focused on large-batch, non-real-time scenarios.
- Optimize GPU memory usage, kernel execution, and communication across nodes (NCCL, MPI, etc.).
- Own CUDA kernels, compiler-level tricks, and multi-GPU scheduling logic.
- Lead profiling and performance tuning for throughput, and cost- down to the kernel level.
- Collaborate with infra, product, and research teams to define SLAs, resource allocation logic, and runtime behaviors.
- Help build the core infrastructure that will run LLM workloads across hybrid GPU environments (cloud/on-prem/self-hosted).

We're looking for a talented AI Security Researcher to join our team and play a critical role in our company's foundational, risk-driven approach to cloud security. This role requires deep technical research into complex cloud- and AI-native environments to identify the most significant, unaddressed risks.
Responsibilities
Conduct deep technical research to discover and report novel risks and attack vectors specific to modern cloud- and AI-native architectures and systems.
Discover and articulate the highest unaddressed risk areas, working with Product and Engineering teams to translate research into product capabilities.
Define necessary foundational product capabilities by delivering both compelling proofs of risk (demonstrating impact) and technical POCs (showing how to solve it).
Work closely with Product and Engineering teams to ensure comprehensive risk coverage and support the investigation of new and complex product scope.

We are seeking a Senior AI Researcher to lead post-training evaluation, red-teaming, and reinforcement learning (RL) gym audits on open-weight models. The ideal candidate will establish rigorous benchmarking methodologies, evaluate large language models (LLMs) against complex threats like Indirect Prompt Injections (IPI), and construct post-training evaluation pipelines that accurately measure realistic frontier-level security capabilities. Key Responsibilities RL Post-Training & Benchmarking
* Execute post-training runs (e.g. GRPO) using mainstream open-weight generalist models against security-focused RL environments, targeting threat vectors like Indirect Prompt Injection (IPI).
* Reward Diagnostics & Trace Analysis - Analyze live loss curves and rollout traces to identify reward hacking, lazy policy convergence, and flawed or over/under-specified verifiers. Task & Environment Auditing
* Review tasks and multi-turn environments (including tool use, web navigation, and computer use) for realism, threat model accuracy, data distribution, and dataset balance. Performance Reporting (Gym Cards)
* Generate comprehensive evaluation cards detailing hill-climbing performance uplift across checkpoints, failure modes, tokens/turns per rollout, and task-level success rates. Integration & Orchestration
* Integrate dockerized environments (e.g., Harbor format) into internal training frameworks, optimizing reset/statefulness semantics, concurrency, and throughput ceilings.
Hybrid:
Yes

This is a research‑first role focused on deeply understanding LLM internals to improve the security of AI agents. Youll design careful experiments on activations and interpretable features- e.g., probing, attribution & ablation/patching, representation‑geometry analyses-to uncover mechanisms behind jailbreak, indirect prompt injection, and other attacks. Then translate those insights into signals that can be used for detection and analysis of a model response.

The field of LLM interpretability at scale is exploding, with several major publications in the last months, and major opportunities for innovation.

Responsibilities:
Investigate model internals, including activation/features analysis, unsupervised clustering, discovery of directions in latent space, etc. It may also require training specific model parts to improve interpretability metrics.
Design security‑grounded evaluations: curate datasets for different attack types, evaluate performance of different white box (model internals) methods compared to black box (input/output only) baselines.
Publish and share: produce our Labs posts and open artifacts; when the work is strong, aim for tier‑1 ML venues (NeurIPS, ICML, etc.) and security forums. A publication of code and/or trained models in cases of community relevant novelty.
Build tools: Several open source libraries exist (like Anthropics attribution graphs infra), but the research in the field is very dynamic, which will require you to build and adapt tools to your own research directions. This also includes agents to automate research work and distill knowledge from designed experiments.

Required Compilation Technology Expert
Job Description
We are forming a new team to explore AI Compilation Boundaries
This team will operate under a unique manner, as described below -
The environment
- Startup-like intensity
Small team
High ownership
High visibility
Merit is the essence, not titles
- Fast pace
Todays state of the art is tomorrows baseline
We aim to go beyond
- Incubator mindset
Take on hard challenges, dismantle, and regroup as novelty
- Elite technical culture
Strong experts
Strong standards
Strong execution.
Ratio beats seniority, not the other way around
- No artificial boundaries
We challenge assumptions, and question constraints, and leave no quarter
- Direct exposure to the latest and greatest AI technology
Real hardware
Real toolchains
Real large-scale AI applications
All pass through and impacted by our work
- First-principles thinking
out-of-the-box is a compromise
Do not accept that a box had to exist in the first place.

Required Research Intern: Next-generation Computer Architecture for Racks and SuperPods
Responsibilities:
The research focuses on designing next-generation rack and SuperPod architectures that combine elasticity through resource pooling with optimal performance enabled by holistic co-design across applications, parallel programming models, interconnect fabrics, and compute, memory, and switch chip architectures. On the communication side, the work architects scalable, high-bandwidth, and low-latency scale-up fabrics across multiple chips at rack and SuperPod scale. On the memory side, it explores richer protocol semantics beyond traditional load/store operations to reduce unnecessary data movement and rethinks memory hierarchies to expose large-scale capacity with near-local latency. On the compute side, it analyzes the requirements of General Compute and Generative AI workloads and their parallel programming models to fully leverage large-scale system resources.
Investigate and prototype new architectural features, including but not limited to:
o Tiered Memory: Explore advanced memory organizations, including hardware-managed caching, to enable software-transparent, fine-grained promotion and demotion of cache lines across the memory hierarchy.
o Prefetching/Speculation: Evaluate and design existing and next-generation hardware prefetching and speculation mechanisms to effectively hide local and remote memory latencies at rack and SuperPod scale.
o Near-Memory/Network Processing: Develop support for key primitives executed at the memory and network layers to minimize unnecessary data movement across sparse, dense, and pointer-based data structures.
o Workload-Centric Co-Design: Study optimal parallelization strategies at rack and SuperPod scale for both General Compute and Generative AI workloads, and design dedicated hardware support for widely used parallel programming primitives such as RPCs and collective communication.
Write reports and papers on the research results and present them.

We are looking for a talented and motivated M.Sc. or Ph.D. student to join our Systems Research team and contribute to advanced research in next-generation computing systems.
In this role, you will:
Participate in research and analysis of state-of-the-art computer systems and emerging technologies.
Investigate system performance, identify bottlenecks, and explore innovative approaches for improving system efficiency, scalability, and performance.
Develop and evaluate Proof-of-Concepts (PoCs) for end-to-end systems and novel architectures for data centers, including AI, Cloud, Storage, Big Data, and distributed computing.
Gain hands-on experience in implementing, testing, benchmarking, and validating new system concepts and architectures.
Work closely with experienced researchers, architects, and engineers on advanced research and development projects.
Explore recent academic research and emerging technologies, identify new research opportunities, and contribute ideas and insights to ongoing research activities.

We are looking for an exceptional researcher at the intersection of artificial intelligence and cybersecurity. This role is intended for someone who combines deep security expertise with a practical understanding of modern AI systems and the curiosity to explore how they can be attacked, abused, and defended.
Key Responsibilities
Research vulnerabilities, attack techniques, and emerging security risks in AI models, agents, applications, and supporting infrastructure.
Develop innovative attacks, proofs of concept, evaluation methods, and defensive solutions.
Analyze how model behavior changes across problem domains, task structures, prompts, tools, resources, harnesses, and model architectures.
Translate research findings into clear security requirements, technical concepts, publications, and practical protections.
Present original research at leading international cybersecurity conferences.
Maintain a strong understanding of developments across the AI and cybersecurity landscapes.
Collaborate with security researchers, AI engineers, product teams, and other stakeholders to turn research into measurable impact.

We are looking for a Senior AI Researcher to join our foundation models team and help advance large-scale models for single-cell RNA (scRNA) data.
In this role, you will focus on training and improving transformer-based and deep learning models, developing algorithmic solutions to challenging modeling problems, and adapting modern foundation model techniques to biological data. This is a hands-on research position for someone who enjoys building and training deep models, understanding their behavior, and pushing them to perform better.
You do not need prior biology experience - but you should be excited to apply your deep learning expertise to a new scientific domain.
Location: Ramat Gan, Israel (hybrid model)
What will you do?
Develop, train, and refine transformer-based and related architectures for large-scale scRNA data.
Tackle challenging modeling problems with thoughtful, principled approaches.
Apply ideas from NLP and vision (pretraining, self-supervision, transfer learning) to biological data.
Plan careful experiments, perform ablations, and deeply analyze results to guide model improvements.
Engage directly with large, noisy biological datasets and build intuition for model behavior in this setting.
Partner with engineers, data scientists, and biology experts to turn research ideas into working systems.

As an AI Researcher, youll be part of the team building the AI systems that power our products. Youll work across research and engineering - from training and post-training state-of-the-art LLMs to applying them to challenging real-world problems such as agentic behavior, coding, and security-related decision-making.

This is a hands-on research role with a strong focus on taking ideas from experimentation to production. Youll have significant ownership and the opportunity to shape both the direction of our AI research and the systems we build around it.

WHAT YOU WILL DO
Train, adapt, and scale state-of-the-art LLMs using techniques such as post-training SFT, knowledge distillation, LoRA, and reinforcement learning.
Develop and evaluate new algorithms and approaches, bridging cutting-edge academic research with production-grade AI systems.
Optimize models for production, balancing quality, latency, throughput, and cost at scale.
Own the AI lifecycle-from algorithmic prototyping and synthetic data generation to evaluation, deployment, and iteration of production AI features.
Work closely with engineering and product teams to translate research advances into impactful AI capabilities.
Lead research initiatives that advance the capabilities of our AI systems.

Join our company, a stealth-mode cybersecurity startup building the next generation of Vulnerability Management and Exposure Management.
Were looking for a Senior AI Researcher (Cyber Security) to join our founding team and build AI-powered product capabilities that enable unprecedented effectiveness in vulnerability and asset management.
In this role, youll work hands-on with large-scale security data (assets, vulnerabilities, exposure context) and design production-grade AI systems that turn messy, complex information into clear, actionable insights.
Own the end-to-end AI lifecycle: from feature ideation and initial research, through data exploration and model development, to delivering reliable, production-grade capabilities. Validate solutions in controlled testing and continuously monitor, evaluate, and improve performance in production.
If you love combining real security problems with applied data science and AI driven problem solving, and want to have real impact in a rapidly evolving product - wed love to meet you.