About the Role
Build reliable agent capabilities that turn advances in reasoning, planning, memory, and tool use into useful product experiences. This role spans agent systems, platform engineering, integrations, and full-stack product development.
What You'll Do
Investigate developments in agent technology and identify valuable product opportunities.
Translate promising model behaviors into reusable skills and workflows that address user needs.
Build and improve Python agent infrastructure, including orchestration, context management, structured outputs, retries, and error recovery.
Design tools and integrations for email, calendars, messaging, browsers, documents, CRMs, and business software.
Own capabilities across Python agents, Django services, APIs, React interfaces, data models, background jobs, observability, and production operations.
Create platform abstractions that make capabilities easier to compose, extend, and maintain.
Improve agent execution latency, cost, reliability, and safety.
Work with evaluation and quality partners to define expected behavior and turn evaluation results into engineering improvements.
Analyze production traces and user feedback to identify and resolve underlying issues.
Guide technical decisions on ambiguous problems and contribute to design reviews.
What We're Looking For
At least 5 years of experience building production software systems end to end, including deployment and operational iteration.
Strong Python skills and hands-on experience with Django, APIs, React, and TypeScript.
Experience building or operating agent systems, including planning, tool calling, structured outputs, context and state management, retries, and orchestration.
Experience designing integrations with external APIs and business software.
Ability to turn loosely defined user needs and emerging technologies into practical product features.
Experience owning complex systems in production, including observability, debugging, and improvements based on production signals.
Skill in designing reusable platform abstractions and diagnosing issues across prompts, model outputs, application code, databases, and APIs.
Background in LLMs, prompt engineering, or production model evaluation is useful, as is experience optimizing high-volume systems for latency, cost, and reliability.
Demonstrated career progression within an organization or experience founding a startup, along with strong engineering fundamentals.
Location
On-site in Palo Alto, California, with hybrid flexibility.