About the Role
Join a core product team building agentic AI systems that automate complex, multi-step workflows across regulated and enterprise domains. You will ship production LLM services and help make them reliable, safe, and useful for customers.
What You'll Do
Design and maintain agentic systems for workflows across healthcare, legal, fintech, logistics, and compliance.
Build and operate RAG pipelines, including vector databases, embeddings, indexing, and domain-specific search.
Develop multi-agent orchestration, tool-calling, memory, and reasoning components.
Create evaluation, testing, and safety infrastructure to measure performance and catch regressions.
Deliver full-stack AI features, from APIs and data models to frontend and backend code, deployment, monitoring, and ongoing operations.
Work with product and design partners to prioritize work, define success measures, and improve features using user feedback and telemetry.
What We're Looking For
Two to eight years of software engineering experience building and shipping user-facing or backend products, preferably at a startup or product-focused company.
Professional experience deploying LLM-based services, including prompt design, orchestration, and tool integration.
Proficiency with Python and TypeScript/React or equivalent, plus cloud platforms such as AWS or GCP and relational or NoSQL databases.
Working knowledge of RAG, vector databases, embeddings, and retrieval pipelines.
Experience building automated tests, evaluations, and monitoring for production AI systems, as well as API-driven, high-throughput systems and real-time features.
Familiarity with agent or workflow frameworks such as LangGraph or CrewAI, and orchestration tools such as Temporal or Trigger.
Experience with multi-tenant or enterprise systems, regulated industries, fine-tuning, or multimodal models is useful.
Compensation & Benefits
Base salary: $150,000 to $180,000 annually. Visa sponsorship is not available.
Location
On-site in San Francisco, California, United States.