Mid-Level AI Engineer

What You'll Do: Design and maintain agentic systems for multi-step workflows across areas such as healthcare, legal, fintech, logistics, and compliance. Build and operate retrieval-augmented generation pipelines, including vector databases, embeddings, indexing, and domain-specific search. Implement multi-agent orchestration, tool calling, memory, and reasoning components. Develop evaluations, automated tests, safety measures, and monitoring to track performance and reliability in production. Ship full-stack features by designing APIs and data models, writing frontend and backend code, and supporting deployment, CI/CD, and production operations. Partner with product and design to set priorities, define success measures, and iterate using user feedback and telemetry.

What We're Looking For: Two to eight years of software engineering experience delivering user-facing or backend products. Production 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 designing API-driven, high-throughput systems and real-time product features, along with production testing and monitoring. Experience with agent or workflow frameworks and orchestration tools is useful. Background in multi-tenant enterprise systems or regulated industries is also relevant. Familiarity with fine-tuning or multimodal models is a plus.

Annual salary: $150,000 to $180,000 USD. Visa sponsorship is not available. Location On-site in San Francisco, California, United States.