Agent Engineer
At a glance
Mid-level AI Engineering role at Clera. Remote, United States · full-time · no salary stated · we estimate $130,000–$203,663 across the United States.
Clera has not published a salary for this role. The figure below is our estimate, not theirs.
remoteroles summary, based on the employer's posting.
What you'll do
- Turn useful new model behaviors into reusable features for real user needs
- Build Python agent infrastructure for orchestration, state, structured outputs, permissions and recovery
- Connect agents to email, calendars, messaging, browsers, documents, CRMs and business software
- Own features across Django services, React interfaces, data models, background jobs and production operations
- Use production traces and user feedback to find reliability problems and improve agent systems
What you bring
- At least five years building production systems in full-stack or backend software engineering
- Strong Python skills, including asynchronous work and complex stateful systems
- Hands-on experience with agent or applied AI systems, including orchestration, tool use and reliability
- A record of taking products or systems from design through deployment, operation and iteration
- Startup founder experience or clear career growth within an organization, plus a degree from a strong engineering program
Who this fits
This role suits an engineer who can work across backend systems and product features, with a strong focus on Python and applied AI. The job is on-site in Palo Alto. Visa sponsorship is unavailable.
From the employer
About the Role
Join a small, senior team building production-grade AI agent capabilities for productivity workflows. You will work across agent systems, platform engineering, integrations, and product development to create reliable experiences users can trust.
What You'll Do
Investigate emerging model capabilities and turn useful behaviors into reusable solutions for real user needs.
Build and evolve Python agent infrastructure for orchestration, context and state management, structured outputs, retries, permissions, and error recovery.
Design integrations with email, calendars, messaging platforms, browsers, documents, CRMs, and business software.
Own features from Python and Django services through React interfaces, data models, background jobs, observability, and production operations.
Analyze production traces and user feedback, diagnose reliability issues, and improve systems at their root cause.
Partner on evaluations, instrumentation, regression analysis, and engineering improvements.
Create platform abstractions that make agent capabilities easier to compose, extend, and maintain.
Improve latency, cost, reliability, and safety, and contribute to technical direction and design reviews.
What We're Looking For
At least 5 years of full-stack or backend software engineering experience building production systems.
Strong Python skills, including maintainable production code, asynchronous systems, abstractions, and complex stateful behavior.
End-to-end ownership of products or systems through design, implementation, deployment, operation, and iteration.
Experience with agent or applied AI systems, including planning, tool calling, structured outputs, context, orchestration, model selection, and reliability; NLP or RAG experience is relevant.
Production experience building backend services, APIs, data models, and integrations across platforms.
Comfort working with Django, React, and TypeScript, alongside backend-focused Python work.
Ability to debug across application code, databases, APIs, models, and external tools, and to build reusable platform abstractions.
Startup experience as a founder or demonstrated career progression within an organization, plus a degree from a strong engineering program.
Experience with an agent framework such as LangChain or AutoGPT is useful.
Compensation & Benefits
Visa sponsorship is not available.
Location
On-site in Palo Alto, United States.