N
Senior AI Engineer
Не указаноПолная занятостьAI EngineeringSemiconductorsAI Infrastructure
Build agent workflows for hardware network simulation and analysis. Develop the context, evaluation, observability, and performance capabilities that make these workflows reliable and useful to network architects.
Обязанности
- Build multi-step agent workflows for hardware network simulation and analysis.
- Develop agent context from simulation models, specifications, design documents, and source code.
- Collaborate with network architects to translate their workflows into agent-based tools.
- Optimize simulation tooling for execution time, compute cost, and end-to-end latency.
- Define evaluation and regression testing for agent workflows and their context sources.
- Build observability into agent runs to track actions and diagnose failures.
- Promote secure and reliable agent workflows, including data handling, access control, and interaction boundaries.
- Resolve complex integration issues between agents and internal tools.
Требования
- At least 5 years of hands-on software engineering experience, including ownership of production systems from design through deployment.
- Expert-level C++ and strong Python programming skills.
- Strong understanding of hardware and full-stack performance, including memory, I/O, networking, and accelerators.
- Practical knowledge of agent systems, including agent loops, tool interfaces, context retrieval and management, and common failure modes.
- Understanding of inference serving, including request lifecycle, batching, caching, throughput, latency, and cost tradeoffs.
- Bachelor’s degree or higher in computer science, computer engineering, or a related field, or equivalent experience.
Будет плюсом
- Experience with hardware simulation software, networking technologies, or silicon and systems teams.
- Experience with inference serving engines, their internals, GPU programming, or performance profiling.
- Experience building or fine-tuning generative models, or developing agent tooling adopted by engineering teams.