Sr. Staff Engineer (GenAI)

What you'll do

• Own the agent architecture and ship reliable, safe production systems with graceful degradation and human handoff.
• Build retrieval, reasoning, and evaluation pipelines, integrating safety, cost, latency, and quality measures.
• Set technical strategy and mentor multiple engineering pods while partnering on automation coverage and rollout.

What they ask for

• 10+ years building production ML/AI systems and 4+ years leading complex ML initiatives end-to-end.
• Deep expertise in LLM-driven systems, including inference optimization, prompt/program design, fine-tuning, distillation/LoRA, safety/guardrails, and evaluations.
• Strong Python skills plus one of Go/Java/C++; hands-on experience with microservices, gRPC/HTTP, cloud infrastructure, containers, CI/CD, and telemetry/observability.
• Demonstrated ownership of high-availability services and a track record of shipping customer-facing intelligent experiences with measurable impact.

Nice to have

• Production experience with agentic architectures and RAG over complex, policy-heavy knowledge bases.
• Experience with large-scale support automation, multilingual NLU/NLG, safety red-teaming, or privacy-by-design.

Pay

USD $267,000 per year - USD $297,000 per year base salary (San Francisco, CA); USD $267,000 per year - USD $297,000 per year base salary (Sunnyvale, CA)

Tools

Python, Go, Java, C++, gRPC/HTTP, CI/CD, RAG, LLM-as-judge

AI focus

Build and scale an autonomous customer-support agent, including agentic planning, memory, LLM orchestration, retrieval and reasoning, evaluations, safety guardrails, multilingual support, and real-time voice.