Drimva

Cheiron

Agent Engineering Intern (Los Altos)

Los Altos · On-site · Internship · Posted Sep 2, 2026

Education
Currently pursuing an undergraduate or master's degree in computer science, computer engineering, or a related technical field.
Visa sponsorship
Candidates of any nationality or visa status may be considered when the internship can be employed legally.

About the job

Build and ship agent-driven workflows for Cheiron’s drug-development platform, including retrieval, tool use, evaluation, and supporting backend services.

What you'll do

  • Design and implement agent workflows with explicit state, task decomposition, tool use, and typed outputs.
  • Build retrieval and citation paths, plus evaluation, tracing, retries, observability, and recovery for multi-step execution.
  • Develop supporting backend services, data models, APIs, and product surfaces, and test workflows against realistic success and failure cases.

What they ask for

  • Currently pursuing an undergraduate or master's degree in computer science, computer engineering, or a related technical field.
  • Strong programming fundamentals and experience building a substantial software project, developer tool, backend system, or open-source contribution.
  • Hands-on experience building a nontrivial agent, retrieval system, tool-using workflow, evaluation harness, or multi-step automation system.
  • Able to work fully in person in Los Altos; semester or quarter interns must commit at least 20 hours per week, and summer interns should be available full time.

Nice to have

  • Experience with Python, FastAPI, Postgres, agent frameworks, retrieval systems, or vector databases.
  • Backend, distributed-systems, infrastructure, data-pipeline, end-to-end product, reliability, or high-stakes correctness experience.

Pay

$35–$55 per hour (hourly compensation)

Tools

Python, FastAPI, Postgres

AI focus

Build agent workflows that decompose objectives, retrieve evidence, use tools, maintain state, recover from failures, and produce structured results for human review.

Model-written summary · the original posting is authoritative

First seen Oct 29, 2026 · Last verified Nov 5, 2026 (UTC)