דרושים » AI » Senior AI Researcher

Required Senior Deep Learning Researcher
About the team:
A pioneering force in the autonomous vehicles (AV) industry.
Join us to build the brain behind the car - a large-scale, multi-task neural network that powers the core of our autonomous stack.
Youll design and train cutting-edge deep learning models tailored for our custom EyeQ chip, tackling end-to-end challenges and deploying real-world solutions.
From novel architectures and advanced training techniques to performance tuning under tight constraints, youll work closely with software and hardware teams to turn research into high-impact, production-ready systems.
If youre a brilliant, hands-on researcher with a passion for shaping the future - this is your launchpad.
Our team is at the forefront of our most advanced AI efforts. As a central hub for deep learning innovation, were trusted with designing the core neural network architecture that powers the companys flagship products. If youre seeking a high-impact role among top-tier researchers and developers - this is the place to be.

We are looking for a Principal AI Security Researcher with deep, hands-on expertise in AI red teaming and AI security to lead and scale RLGyms AI security research efforts.
This is not a traditional cybersecurity leadership role. We need someone who has directly worked on breaking, attacking, testing, and securing AI systems, particularly large language models (LLMs), generative AI applications, and agentic AI systems.
The ideal candidate has significant practical experience designing and executing AI red-team programs, developing adversarial attacks, identifying AI-specific vulnerabilities, building automated red-teaming capabilities, and translating findings into effective guardrails and security protections.
What you'll be doing:
Lead and scale multidisciplinary teams focused on AI red teaming, adversarial testing, and AI security research.
Design and execute sophisticated attacks against LLMs, GenAI applications, and agentic AI systems.
Research attack techniques including prompt injection, jailbreaks, indirect prompt injection, tool abuse, agent manipulation, data leakage, model misuse, and adversarial behavior.
Build and evolve AI red-teaming engines and automated adversarial testing systems, including RLGym.
Building and scaling global AI security teams (red teaming, adversarial research, guardrails engineering) while fostering an innovation-driven security culture.
Overseeing advanced adversarial evaluations for GenAI models, agentic AI, and multi-agent (A2A) systems
Defining and implementing AI red-teaming frameworks aligned with OWASP AI Security guidelines, MITRE ATLAS, and NIST AI RMF, and operationalizing automated red-team engines to continuously stress-test models at scale.
Partnering with product and engineering to design and deploy enterprise-ready AI guardrails - including policy enforcement layers, monitoring pipelines, and anomaly detection systems - and championing secure deployment practices for GenAI (including agent orchestration via MCP and A2A workflows).

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.
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!

Alice is seeking a highly skilled, resilient, and technical Child Safety Researcher to join our team. In this role, you will be on the front lines of investigating complex online child safety violations, handling sensitive content reviews, and developing technical automations to scale our policy and enforcement operations. This is a high-impact, multi-faceted position that requires blending deep domain expertise in child safety with hands-on scripting and data engineering skills to transform raw queue data into actionable signals and automated review processes.
Key Responsibilities
* Investigate & Evaluate Complex Cases: Review, validate, and adjudicate high-risk, graphic, and sensitive child safety content, navigating nuanced contexts involving legal, medical, or parental scenarios.
* Extract Signals & Insights: Analyze review queues, large datasets, and user-generated content to identify new adversarial shifts, unknown unknowns, and critical keywords that inform policy updates.
* Build Local Automations & Scripts: Design, write, and maintain scripts and local tools to automate review workflows, generate suggestions, and increase overall queue efficiency.
* Policy & Enforcement Collaboration: Translate raw investigation findings into structured intelligence reports and actionable recommendations for client policy frameworks and engineering teams.
* Quality & Model Support: Partner with product and AI teams to label golden datasets, support ML-based labeling QA, and improve automated detection models.

About Alice:
Alice is 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, Alice 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. Alice is 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!