$200,000 - $300,000
San Francisco, Hybrid
Full-time / Permanent
A product-focused AI start-up is building LLM systems that run in production and are used daily by over a million professionals. This role is responsible for designing, shipping, and maintaining applied LLM systems that support real product features, with an emphasis on reliability, cost, and scale rather than experimentation.
Why This Role Matters
- Own how LLM systems behave in a large, user-facing product
- Make architectural decisions that affect reliability, latency, and cost
- Move LLM features from prototype to stable production systems
- Set technical direction for applied LLM algorithms and evaluation practices
What You’ll Do
- Design structured LLM workflows, including planning, reasoning, and multi-step execution
- Build and maintain core components such as memory, personalization, and reusable LLM modules
- Lead development of LLM-powered product features from design through production
- Build and optimize retrieval pipelines (RAG) via chunking, indexing, reranking, and evaluation
- Select and route between models based on performance, cost, and latency constraints
- Define evaluation metrics, monitoring, and feedback loops
- Debug production issues and drive algorithm-level improvements
What You Bring
- Experience shipping LLM-based systems into production
- Strong understanding of prompting, reasoning workflows, and system design
- Hands-on experience with RAG systems
- Experience building evaluation, monitoring, or safety mechanisms
- Ability to lead technical decisions and guide other engineers
- Experience with inference optimization, efficiency, or large-scale systems is a plus
