Los Altos, CA · Engineering · Internship · Semester/quarter or summer · Fully in-person

Company Overview

In July 2026, Cheiron announced an $8 million seed round led by Menlo Ventures, bringing total funding to $13 million to date, with the backing and strategic support of industry veterans including Moderna co-founder and MIT Institute Professor Robert Langer, former Pfizer Chief Medical Officer Freda Lewis-Hall, Chai Discovery co-founder and CEO Josh Meier, former Starbucks CEO Laxman Narasimhan, and former Apple AI chief John Giannandrea.

Cheiron is building the first AI-native operating system designed to represent an entire drug program as a single connected system. The company's platform helps biopharma teams represent, reason over, and stress-test the full state of a drug development program, including the claims, evidence, assumptions, risks, decisions, and commitments that determine whether a therapy advances. In less than six months since launch, Cheiron has been adopted by tens of thousands of biopharma professionals and deployed by major drug developers, and is already used by 7 of Korea's top 10 biopharma companies.

Cheiron is expanding into pharmaceutical CMC (Chemistry, Manufacturing, and Controls) teams. CMC governs how a drug is made, tested, and kept consistent across its entire commercial life. The work involves hundreds of regulatory commitments, post-approval changes, and cross-market submissions. Today it runs on documents, spreadsheets, and institutional memory. Cheiron augments manual workflows with a CMC regulatory-specific intelligence and reasoning layer.

Founded in 2024 by Stanford-trained AI researchers. The team includes leaders with combined decades of experience across pharma and biotech. Headquartered in Los Altos, California. We are building and deploying the product now with rapid expansion into global markets.

About the Role

We're looking for an Agent Engineering Intern to build new agent-driven workflows inside Cheiron's product.

Cheiron's agents do more than generate an answer. They break complex objectives into steps, retrieve evidence, call tools, maintain state across long-running work, recover from failures, and produce structured results that a person can review and trust. You will own a bounded workflow and help take it from an ambiguous problem to a reliable, working product.

This is an Applied Engineering Role. We care about strong software fundamentals, hands-on ownership, and evidence that you have built nontrivial systems yourself. The role is best suited to undergraduate and master's students who are already serious builders.

What You'll Do

Design and implement new agent workflows with explicit state, task decomposition, tool use, and typed outputs.

Build retrieval and citation paths that ground important outputs in source evidence.

Add evaluation, tracing, retries, observability, and recovery behavior for multi-step execution.

Build the backend services, data models, APIs, and focused product surfaces required to make the workflow useful.

Test agent behavior against realistic success cases, failure cases, and incomplete evidence.

Work directly with engineers and domain experts, demonstrate progress frequently, and make pragmatic scope decisions.

Requirements

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.

Clear personal ownership of the work: you can explain what you implemented, the decisions you made, and what you would improve.

Ability to reason about state, failure modes, grounding, evaluation, and engineering tradeoffs—not only prompts and model selection.

High agency and comfort working through ambiguous problems in a fast-moving environment.