1 day ago
San Francisco, CA, USAMid Level / Senior
Responsibilities
- Design, build, and maintain agentic systems that automate complex multi-step workflows.
- Own production RAG pipelines and retrieval infrastructure, including vector databases, embeddings, and indexing.
- Implement multi-agent orchestration, tool-calling, memory, and reasoning components.
- Develop evaluation and safety infrastructure for model performance, regressions, trust, and reliability.
- Ship full-stack AI products by implementing APIs, data models, frontend and backend code, and production operations.
- Collaborate with founders, product, and design to prioritize work, define success metrics, and iterate using user feedback and telemetry.
Requirements
- 2 to 8 years of software engineering experience shipping user-facing or backend products.
- Hands-on production experience deploying LLM-based services, including prompt design, orchestration, and tool integration.
- Full-stack proficiency in Python and TypeScript/React or equivalent.
- Experience with AWS or GCP and relational or NoSQL databases.
- Working knowledge of RAG patterns, vector databases, embeddings, and retrieval pipelines.
- Experience building automated tests, evaluations, and monitoring for AI systems.
- Familiarity with LangGraph, CrewAI, Temporal, or Trigger.
- Background in multi-tenant or enterprise-ready systems or regulated industries such as healthcare, fintech, or legal.
- Experience designing API-driven, high-throughput systems and real-time product features.
- Ability to deliver end-to-end features from data modeling through deployment and monitoring.
Benefits
- On-site work in San Francisco, California; candidates must be able to work in-office or relocate.
- Visa sponsorship is not available for this role.