Agent Engineer
About the Role
This is an Agent Engineer role at an early-stage AI productivity startup building an autonomous executive assistant. You will work at the intersection of agent systems, platform engineering, integrations, and product development, turning frontier model capabilities into reliable features that users can trust with real work.
What You'll Do
Investigate advances in reasoning, planning, memory, tool use, and agent collaboration to identify new product capabilities.
Translate promising model behaviors into reliable, reusable skills and workflows that solve real user problems.
Build and evolve a custom Python agent harness, including execution loops, orchestration, context management, structured outputs, retries, and error recovery.
Design agent tools and integrations across email, calendars, messaging platforms, browsers, documents, CRMs, and business software.
Own capabilities end-to-end across the Python agent, Django services, React interfaces, data models, background jobs, observability, and production operations.
Build platform abstractions that make capabilities easier to compose, extend, and maintain as the product grows.
Improve latency, cost, reliability, and safety across high-volume agent execution.
Work with the Agent Evaluations and Quality team to define expected behavior and turn quality findings into engineering improvements.
Study production traces and user feedback to understand where users lose trust, then fix the underlying system.
Set technical direction on ambiguous problems and raise the engineering standard through design reviews and thoughtful execution.
What We're Looking For
5+ years building production software systems end-to-end, including design, implementation, deployment, and operational iteration.
Strong Python proficiency: maintainable production code, asynchronous systems debugging, and sound abstraction design.
Hands-on experience building agent systems: planning, tool calling, structured outputs, context and state management, retries, and orchestration.
Full-stack capability across backend services (Python/Django), APIs, and frontend interfaces (React/TypeScript).
Experience designing and building integrations with external APIs and business software platforms such as email, calendars, messaging, and CRMs.
Ability to translate emerging technical capabilities and vague user needs into concrete product features without complete specifications.
Experience designing reusable platform abstractions that enable composition, extension, and maintenance at scale.
Experience analyzing production traces, logs, and user feedback to identify root causes across prompts, model outputs, application code, databases, and APIs.
Familiarity with LLMs, prompt engineering, or model evaluation in production systems is a strong plus.
Experience with agent frameworks or orchestration platforms (such as LangChain or AutoGen) is a plus.
Background in autonomous systems, workflow automation, or high-volume distributed systems optimization is welcome.
Location
Hybrid, based in Palo Alto, United States. Visa sponsorship is not available.