Join a product engineering team building dependable AI agent capabilities for productivity workflows. You will turn advances in reasoning, planning, memory, and tool use into reliable features that users can trust with real work.
Explore new agent capabilities and identify useful product opportunities.
Build reusable skills and workflows that address practical user needs.
Develop a Python agent harness for orchestration, context management, structured outputs, retries, and error recovery.
Design integrations with email, calendars, messaging platforms, browsers, documents, CRMs, and other business software.
Own capabilities across Python and Django services, APIs, React interfaces, data models, background jobs, observability, and production operations.
Create platform abstractions that make agent capabilities easier to compose and maintain.
Improve latency, cost, reliability, and safety across agent execution.
Use evaluations, production traces, and user feedback to diagnose issues and improve system quality.
Set technical direction for ambiguous problems and contribute to design reviews.
At least 5 years of experience building and operating production software systems end to end.
Strong Python skills, including maintainable production code and asynchronous systems; experience with Django, APIs, React, and TypeScript.
Hands-on experience with agent systems, including planning, tool calling, structured outputs, context and state management, retries, and orchestration.
Experience building integrations with external APIs and business software.
Ability to translate evolving technology and loosely defined user needs into practical product features.
Experience designing reusable systems and platform abstractions, and owning production observability, debugging, and iteration.
Strong analytical debugging skills across prompts, model outputs, application code, databases, APIs, and user interactions.
Background in LLMs, prompt engineering, or model evaluation in production is useful, as is experience optimizing distributed systems or building autonomous systems and workflow automation.
Strong computer science and engineering fundamentals, clear communication, and a record of sustained growth in a role or startup experience.
Visa sponsorship is not available.
On-site in Palo Alto, California, United States.
Build and deliver AI-powered healthcare products, developing full-stack features, APIs, backend services, and LLM integrations while collaborating with product and clinical teams and applying software, DevOps, and MLOps practices.
Build reliable AI coding-agent workflows and open-source tools that help engineering teams identify and fix instrumentation issues across codebases, while improving agent quality, reliability, and cost.
Own the design and production delivery of enterprise AI systems, embedding with client teams to understand operational needs, ship GenAI solutions, and shape AI adoption from strategy through deployment.
Develop AI agents, orchestration, and guided workflows for an enterprise AI platform, building conversational experiences and integrating agent capabilities with backend systems and observability tools.
Develop AI agents, orchestration, and conversational workflows for an enterprise AI platform, integrating Python, LangGraph, and LangChain with backend systems and observability tools.
