(Senior) Machine Learning Engineer / Data Scientist

ProFound•Boston, MA

2d•$96,000 - $214,500

About The Position

ProFound Therapeutics is pioneering the discovery of the expanded human proteome to unlock a new universe of potential therapeutics. By integrating multi-omics, advanced computation, and translational biology, we aim to reveal and characterize thousands of previously uncharted proteins and systematically explore their role in health and disease. We are seeking a highly motivated Senior Machine Learning Engineer / Data Scientist to join our AI/ML team. This individual will play a central role in designing and implementing advanced AI/ML systems with a focus on Retrieval-Augmented Generation (RAG), graph-based RAG, large language models (LLMs), agentic orchestration, and conversational AI (chatbot) solutions. Working closely with the Head of AI/ML and cross-functional partners, you will build and optimize LLM-powered pipelines and multi-agent systems that integrate knowledge graphs, multi-omics data, and biological context to uncover disease-driving proteins and pathways. The insights generated will directly support therapeutic discovery and development.

Requirements

Ph.D. in Computer Science, Machine Learning, Applied Mathematics, Computational Biology, or related field with 1–3 years of industry experience (preferred); or M.S. in a related field with 4–6 years of industry experience.
Proven track record in building LLM-based applications, with hands-on expertise in RAG, graph-based RAG, agentic orchestration, and/or chatbot development.
Proficiency in Python and LLM/ML frameworks such as LangChain, Hugging Face Transformers, PyTorch, or similar.
Strong experience with knowledge graph technologies, graph databases, and vector databases.
Demonstrated ability to work in cross-disciplinary teams, communicate complex ideas clearly, and deliver results in fast-moving environments.

Nice To Haves

Experience working with multi-omics or high-dimensional biological data is a plus
Familiarity with probabilistic modeling, causal reasoning, or statistical inference is a plus.

Responsibilities

Architect and implement scalable RAG and LLM-based systems that integrate multi-modal data sources, including knowledge graphs, documents, and structured biological datasets.
Design and deploy RAG and graph-based RAG pipelines that leverage LLMs and knowledge graphs to retrieve, reason over, and synthesize complex biological information.
Build and maintain agentic orchestration frameworks (multi-agent systems) that coordinate LLM-based agents for end-to-end scientific reasoning, data retrieval, and decision support.
Collaborate with data engineering teams to design data pipelines that harmonize and prepare large-scale omics datasets for model training.
Develop and optimize conversational AI (chatbot) interfaces that enable scientists and stakeholders to query, explore, and interact with internal data and model outputs using natural language.
Partner with experimental scientists to ensure model outputs are biologically interpretable and experimentally testable.
Stay abreast of advances in LLMs, RAG architectures, agentic AI, and conversational AI; bring innovative ideas into the team.