ProFound Therapeutics: AI/ML Engineering - SAGE Platform Co-Op

Flagship Pioneering • Cambridge, MA

23h • Hybrid

About The Position

ProFound Therapeutics’ AI/ML team builds SAGE, an internal multi-agent LLM platform that helps scientists reason over knowledge graphs, biological databases, and scientific literature. As an AI/ML Engineering Co-Op, you will extend SAGE’s capabilities and improve its reliability, owning features from design through deployment in collaboration with ML engineers and the scientists who use the platform. The role provides hands-on experience building and operating a production AI system in a drug discovery setting.

The work includes developing agent tools and integrations, document ingestion and retrieval, user experience and collaboration features, LLM evaluation and benchmarking, and monitoring of usage, performance, reliability, and cost. The position is full-time, 40 hours per week, with a hybrid schedule in Watertown, Massachusetts, for the January–June 2027 co-op period. It is open exclusively to current Northeastern University co-op students.

By the end of the co-op, the goal is to have deployed at least one new SAGE capability used by scientists, established a regularly running evaluation and benchmarking pipeline, improved visibility into usage, performance, and cost, and produced documented work the team can maintain. The role is a short-term engagement and is not eligible for health and welfare benefits; retirement benefits may be available after completing a set number of hours. The pay range is $25–$35 per hour.

Requirements

• Currently pursuing a B.S. or M.S. in Computer Science, Artificial Intelligence, Data Science, or a related field.
• Available for a full-time, 4–6 month co-op term.
• Strong Python skills.
• Hands-on experience building with LLMs, such as through LLM APIs, RAG, agents, or MCP, gained through coursework, projects, or prior internships.
• Familiarity with Git and software engineering best practices, including testing, code review, and documentation.
• Curiosity, self-direction, and the ability to communicate clearly with technical and non-technical colleagues.
• Must be a current Northeastern University co-op student.

Nice To Haves

• Experience with web or backend development, such as FastAPI, React, or TypeScript.
• Experience with LLM evaluation frameworks or observability and tracing tools.
• Exposure to knowledge graphs, vector databases, or scientific and biological data sources.
• Familiarity with cloud environments such as AWS, containers such as Docker, and CI/CD tooling such as GitHub Actions.
• Prior software or ML engineering internship or co-op experience.
• Interest in biology or drug discovery; biology background is not required.

Responsibilities

• Design, build, and ship SAGE tools connecting 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 components spanning knowledge graphs, biological databases, and scientific literature.
• Build SAGE chat interface features, such as conversation sharing and displaying sources and citations.
• Gather feedback from scientists and turn it into practical, prioritized improvements.
• Develop evaluation and benchmarking pipelines measuring answer quality, accuracy, and hallucination rate.
• Help build and curate benchmark datasets with scientists, using automated and human-review approaches.
• Integrate automated quality checks and regression tests into the CI/CD pipeline.
• Build monitoring for SAGE usage, performance, reliability, and LLM cost.
• Write clean, tested, and documented code and participate in code reviews.
• Present progress and results to the AI/ML team and scientific stakeholders, including a final co-op presentation.

Benefits

• Mentorship from experienced ML engineers.
• Access to Flagship Pioneering Co-Op Program enrichment sessions, a dedicated professional development track, and a mentor.
• Potential consideration for future opportunities across Flagship and its portfolio companies.
• Pay of $25–$35 per hour.
• Retirement benefits may be available after completing a set number of hours.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern