4 days ago
Palo Alto, CA, USASenior
Responsibilities
- Investigate reasoning, planning, memory, tool use, and agent collaboration advances to identify product opportunities.
- Translate model behaviors into reliable, reusable agent skills and workflows.
- Build and evolve a custom Python agent harness with orchestration, context management, structured outputs, retries, and error recovery.
- Design tools and integrations across business software including email, calendars, messaging platforms, browsers, documents, and CRMs.
- Own capabilities across the Python agent, Django services, React interfaces, data models, background jobs, observability, and production operations.
- Build reusable platform abstractions and improve latency, cost, reliability, and safety across agent execution.
- Partner with Agent Evaluations to define expected behavior and turn quality findings into engineering improvements.
- Use production traces and user feedback to diagnose trust issues and improve the underlying system.
- Set technical direction on ambiguous problems and raise engineering standards through design reviews and execution.
Requirements
- At least 5 years of experience building production software systems end-to-end, including design, implementation, deployment, and operational iteration.
- Strong Python proficiency, including maintainable production code, asynchronous systems, and sound abstractions.
- Hands-on experience building agent systems with planning, tool calling, structured outputs, context and state management, retries, and orchestration.
- Deep Python and Django expertise with full-stack capability and comfort with APIs, React, and TypeScript.
- Experience designing integrations with external APIs and business software platforms such as email, calendars, messaging, and CRMs.
- Experience designing reusable platform abstractions for composition, extension, and maintenance at scale.
- Strong analytical debugging skills across prompts, traces, model outputs, application code, databases, and user interactions.
- Product judgment for turning vague user needs and emerging technical possibilities into useful capabilities.
- Strong computer science fundamentals, ideally from an engineering-focused academic background.
- Prior startup experience or demonstrated increasing ownership within a single organization.
- Familiarity with LLM-based systems, prompt engineering, or production model evaluation is a plus.
- Experience with LangChain or AutoGen is a plus.
- Background in workflow automation, autonomous systems, or distributed-systems optimization is a plus.
Benefits
- The role is on-site in Palo Alto, California, with hybrid flexibility.
- Visa sponsorship is not available for this role.