About the role#
ProFound Therapeutics is looking for an AI/ML Engineering Co-op to join the team building SAGE, an internal multi-agent LLM platform. SAGE helps our scientists reason over knowledge graphs, biological databases, and scientific literature to accelerate drug discovery. In this role, you will own features from design through deployment, working alongside ML engineers and scientists to extend the platform and ensure its reliability.
What you'll do#
- Design, build, and ship new SAGE tools that connect the agent to external data sources, APIs, and MCP servers.
- Extend SAGE’s ability to ingest and reason over user-uploaded documents, including parsing, chunking, and retrieval.
- Contribute to agent orchestration and retrieval-augmented generation (RAG) components.
- Build features to improve the SAGE chat interface and gather direct feedback from scientists to drive improvements.
- Develop evaluation and benchmarking pipelines to measure answer quality, accuracy, and hallucination rates.
- Help build and curate benchmark datasets using automated and human-review approaches.
- Integrate automated quality checks and regression tests into our CI/CD pipeline.
- Build monitoring for SAGE usage, performance, reliability, and LLM cost.
- Write clean, tested, and documented code while participating in code reviews.
- Present progress and results to the AI/ML team and scientific stakeholders.
What you'll need#
- Currently pursuing a B.S. or M.S. in Computer Science, Artificial Intelligence, Data Science, or a related field.
- Availability for a full-time, 4-6 month co-op term.
- Strong Python skills.
- Hands-on experience building with LLMs, such as LLM APIs, RAG, agents, or MCP.
- Familiarity with Git and software engineering best practices like testing and documentation.
- A curious, self-driven approach with clear communication skills.
- Preferred: Experience with web or backend development (FastAPI, React, or TypeScript).
- Preferred: Experience with LLM evaluation frameworks or observability and tracing tools.
- Preferred: Exposure to knowledge graphs, vector databases, or scientific data sources.
- Preferred: Familiarity with cloud environments (AWS), containers (Docker), and CI/CD tooling (GitHub Actions).
- Preferred: Prior internship or co-op experience in software or ML engineering.
- Preferred: Interest in biology or drug discovery.
Location & details#
- Location: Watertown, Massachusetts.
- Term: Winter 2027 or Summer 2027 (January 2027 to June 2027).
- Modality: Hybrid.
- This is a full-time, paid position.
About Flagship Pioneering
Flagship Pioneering is a biotechnology firm based in Cambridge, Massachusetts. Founded in 2000, the company focuses on inventing and building platform companies that develop products for human health and sustainability. It has originated more than 100 scientific ventures since its inception. The current ecosystem includes over 40 companies, such as Indigo Agriculture and Generate:Biomedicines.
How to get in at Flagship Pioneering
Applying early is a significant advantage when pursuing an internship at Flagship Pioneering, as recruiters often review candidates before the applicant pool becomes unmanageable. Intern Insider sends an instant alert the moment a role matching your target is published, helping you secure a spot at the front of the line. You can reach out to recruiters directly to ask about the role or a potential referral, which often improves your response rates compared to submitting through a general queue. Intern Insider surfaces the specific recruiters behind these roles so you can make that connection yourself.
