דרושים » חשמל ואלקטרוניקה » senior software engineer, deep learning inference

our company is seeking a sharp, innovative, and hands-on architect to help shape the future of llm inference at scale. join our dynamic e2e architecture group, where we build cutting-edge systems powering the next generation of generative ai workloads. in this role, you will work across software and hardware domains to design and optimize inference infrastructure for large language models running on some of the most advanced gpu clusters in the world.
youll help define how ai models are deployed and scaled in production, driving decisions on everything from memory orchestration and compute scheduling to inter-node communication and system -level optimizations. this is an opportunity to work with top engineers, researchers, and partners across our company and leave a mark on the way generative ai reaches real-world applications.
 
what youll be doing:
design and evolve scalable architectures for multi-node llm inference across gpu clusters.
develop infrastructure to optimize latency, throughput, and cost-efficiency of serving large models in production.
collaborate with model, systems, compiler, and networking teams to ensure holistic, high-performance solutions.
prototype novel approaches to kv cache handling, tensor/pipeline parallel execution, and dynamic batching.
evaluate and integrate new software and hardware technologies relevant to model inference (e.g., memory hierarchy, network topology, modern inference architectures).
work closely with internal teams and external partners to translate high-level architecture into reliable, high-performance systems.
author design documents, internal specs, and technical blog posts and contribute to open-source efforts when appropriate.

our company has been redefining computer graphics, pc gaming, and accelerated computing for more than 25 years. its a unique legacy of innovation thats fueled by great technology-and amazing people. today, were tapping into the unlimited potential of ai to define the next era of computing. an era in which our gpu acts as the brains of computers, robots, and self-driving cars that can understand the world. doing whats never been done before takes vision, innovation, and the worlds best talent. being an employee means being part of a diverse and encouraging setting that encourages everyone to perform at their peak. come join the team and discover how you can develop a lasting influence on the world. 
our company is in search of a Senior Software Architect - a creative, forward-thinking, and practical researcher to improve the framework for widespread llm learning and prediction. as part of our dynamic e2e architecture group, you will design and optimize systems driving generative ai workloads, working at the intersection of software and hardware on some of the most advanced gpu clusters worldwide. you will define how ai models are deployed and scaled in production using the spectrum-x networking platform, influencing decisions from inter-node communication and compute scheduling to system -level optimization. this is an opportunity to collaborate with best-in-class engineers and researchers and shape the future of generative ai in real-world applications. your work will make a lasting impact by enabling generative ai technologies to reach real-world applications and improve global computing capabilities. 
what youll be doing: 
lead research and development of end-to-end networking solutions for distributed ai training and inference at scale, with a focus on job completion time, failure resiliency, telemetry, scheduling, and placement.
analyze current deployments, develop prototypes, and recommend architectural improvements. 
stay abreast of the latest research; become the teams authority in emerging networking techniques and technologies. 
design, simulate, and validate new systems using novel, scalable network simulator nsx. 
develop and TEST prototypes on large-scale gpu clusters (e.g., israel-1). 
collaborate across hardware, firmware, and software teams to translate ideas into real networking product features. 
publish patents and present research at leading conferences.

looking for a strong technical senior architect to join us in shaping the future. senior architects are innovators who can translate business needs into workable technology solutions. their expertise is deep and broad. they are hands on, producing both detailed technical work and high-level architectural designs.
as a senior architect in the ai networking research team, you will explore technological challenges on accelerate networking and building ai data centers. research new transport functions and semantics for optimizing ai workloads, ai systems communication and accelerations and much more. you will also be leading architectural and development efforts across numerous technological fields, related to the modern ai data center, such as distributed ai and deep learning solutions, data analytics, high performance computing (hpc), software defined networking (sdn), virtualization, Storage, and more.
what youll be doing:
co-design hardware features (e.g., in gpus, dpus, or interconnects) that accelerate data movement and enable new capabilities for inference and model serving. 
identify and evaluate new technologies, innovations and partner relationships for alignment with our technology roadmap and business value.
lead architecture and design of new technologies and innovations such as runtime systems, communication libraries, ai-specific technologies.
lead proof-of-concept development to evaluate and drive such technologies.

Were growing fast, and our team is passionate about pushing AI engineering to new heights - solving complex problems in LLM training, inference optimization, reasoning, and agent orchestration at scale.
About the Role:
As a Machine Learning Engineer, youll work on cutting-edge
code-focused LLMs and AI agent systems
that power next-generation developer platform. Youll be at the center of research, model training, and productionization of intelligent systems that understand software deeply, collaborate with developers, and help automate engineering workflows end-to-end. Your work will immediately impact millions of engineers worldwide.
Responsibilities:
Push LLM Innovation: Research, design, and fine-tune domain-specific LLMs for code generation, refactoring, debugging, and multi-turn reasoning.
Agent-Oriented Development: Build multi-agent coding systems that integrate retrieval-augmented generation (RAG), code execution, testing, and tool use to create autonomous, context-aware coding workflows.
Production-Grade AI: Own the training-to-inference pipeline for large code models-optimize inference with quantization, distillation, and caching techniques.
Rapid Experimentation: Prototype and validate ideas quickly; leverage reinforcement learning, human feedback, and synthetic data generation to push accuracy and reasoning.
Cross-Functional Collaboration: Partner with product, engineering, and design teams to ship AI-powered features that help developers focus on high-impact work.
Scale the Platform: Contribute to distributed training, scalable serving systems, and GPU/TPU-efficient architectures for ultra-low-latency developer tools.

Help build an Always-On, low-overhead GPU profiling service that runs in production, scales across cluster environments, and delivers actionable insights for ML workloads. You will be hands-on delivering our profiling solutions across system software, drivers, and CUDA to make profiling continuously available and reliable.

What youll be doing:

Develop low-overhead, high-reliability implementations in C/C++, with bounded CPU/memory budgets.

Lead end-to-end feature delivery spanning user-mode components, driver/platform layers, and performance counter/trace providers.

Establish profiling models that integrate with existing ML/AI workflows (e.g., PyTorch/XLA) to turn low-level signals into actionable insights.

our company has evolved ai infrastructure by merging gpu virtualization with kubernetes-native capabilities. our world class ai platform allows organizations to improve productivity and efficiency for data scientists and Machine Learning engineers. with deep kubernetes expertise and a focus on innovation, we are dedicated to developing cutting-edge technologies, delivering the best User Experience for our customers, and providing deep visibility into workload performance through rich metrics that help users optimize their ai workloads. we are looking for highly skilled software engineers to join our platform group and help shape the future of ai infrastructure.
the role of a senior software engineer in the platform group is to design and develop scalable, high-performance systems that support the next generation of ai workloads. you will collaborate with experts across domains, tackle complex challenges, and drive innovations that empower our users to push the limits of ai capabilities.
what youll be doing:
designing and developing enterprise-grade systems with a strong focus on scalability, reliability, and performance.
building and optimizing microservices-based architectures using kubernetes and cloud-native technologies.
collaborating closely with backend engineers, product managers, and other collaborators to deliver impactful solutions.
writing clean, maintainable, and testable code in go
conducting code and design reviews to uphold high-quality standards and mentor team members.

We're looking for a Senior AI/MLOps Engineer to join a group that specializes in Security and Networking, and specifically ML, AI and agent development. As a Senior AI/MLOps Engineer, youll build and maintain the infrastructure, tools and processes necessary to support the AI lifecycle in a production environment. You will collaborate closely with data scientists, software engineers, security architects and DevOps teams to ensure smooth deployment, modeling and optimization of AI models. This role involves creative problem solving alongside engineering teams, and is pivotal for the continued success of AI networking security.

What youll be doing:

Developing, improving and optimizing scalable infrastructure for handling and deploying security and networking AI models and agents in production, ensuring high availability, scalability, reproducibility, and performance.

Optimizing AI models and agents for performance, scalability, and resource utilization, considering factors such as latency, efficiency, and cost.

Monitoring and deploying agentic systems, LLMs, and ML models in production.

Designing and implementing frameworks/pipelines for AI training, inference, and experimentation.

Collaborating closely with data scientists, security architects and software engineers to operationalize and deploy AI models and agents, including packaging and integration with existing systems. Participate in developing and reviewing code, design documents, use case reviews, and test plan reviews.

Collaborating with DevOps teams to integrate pipelines and workflows into the CI/CD process, ensuring flawless deployments and rollbacks.

Building and maintaining monitoring and alerting systems to proactively identify and resolve issues relating to quality, performance and infrastructure.

Implementing access controls, authentication mechanisms, and encryption standards for AI models and data.

Documenting guidelines, and standard operating procedures for MLOps/AI processes and sharing knowledge with the wider team.

Develop proof-of-concepts for new features.

help build an always-on, low-overhead gpu profiling service that runs in production, scales across cluster environments, and delivers actionable insights for ml workloads. you will be hands-on delivering our profiling solutions across system software, drivers, and cuda to make profiling continuously available and reliable.
what youll be doing:
develop low-overhead, high-reliability implementations in C / C ++, with bounded cpu/memory budgets.
lead end-to-end feature delivery spanning user-mode components, driver/platform layers, and performance counter/trace providers.
establish profiling models that integrate with existing ml/ai workflows (e.g., pytorch/xla) to turn low-level signals into actionable insights.

our company is leading the way in groundbreaking developments in artificial intelligence, high performance computing and visualization. the gpu, our invention, serves as the visual cortex of modern computers and is at the heart of our products and services. our work opens up new universes to explore, enables amazing creativity and discovery, and powers what were once science fiction inventions from artificial intelligence to autonomous cars.
come work for the team that brought to you nccl, nvshmem & gpudirect. our gpu communication libraries are crucial for scaling deep learning and hpc applications! we are looking for a motivated partner enablement engineer to guide our key partners and customers with nccl. most DL /hpc applications run on large clusters with high-speed networking (infiniband, roce, ethernet). this is an outstanding opportunity to get an end to end understanding of the ai networking stack. are you ready for to contribute to the development of innovative technologies and help realize our vision?
what you will be doing:
engage with our partners and customers to root cause functional and performance issues reported with nccl
conduct performance characterization and analysis of nccl and DL applications on groundbreaking gpu clusters
develop tools and automation to isolate issues on new systems and platforms, including cloud platforms (azure, aws, gcp, etc.)
guide our customers and support teams on hpc knowledge and standard methodologies for running applications on multi-node clusters
document and conduct trainings/webinars for nccl
engage with internal teams in different time zones on networking, gpus, Storage, infrastructure and support.

We are seeking a skilled software engineer to join our NPU software stack development team. This role involves developing high-performance GPU programming frameworks, runtime systems, and libraries for AI/ML workloads. You will be responsible for implementing, optimizing, and maintaining GPU software stack components to support distributed AI training and inference.
Key Responsibilities
Identify bottlenecks, analysis and optimize in distributed NPU eco-system
Design and develop NPU memory management system
Design and develop optimized NPU development framework, execution path and debugging
Develop compatibility with AI frameworks (Triton, PyTorch, JAX)
Write high-quality, well-tested code with comprehensive documentation
Collaborate with other teams (Hardware, Network, QA, AI Framework Integration)
Participate in code reviews and technical design discussions.