Staff Machine Learning Researcher - Biological Foundational Models

About Somite

Somite.ai is a venture-backed company aiming to become the OpenAI of stem cell biology, developing AI foundation models for human stem cells to drive novel cell therapies at scale.

We take a full-stack approach - generating data at 1,000x lower cost, training large-scale models with unmatched predictive power, and using these models to discover, refine, and optimize high-impact applications in cell therapy.

Our founding team includes repeat AI entrepreneur Dr. Micha Breakstone (Chorus.ai, acquired for $575M), the Head of the Fundamental AI Group at MIT (pioneered the foundational research on scaling laws), and three Harvard Medical School professors and National Academy of Sciences/Medicine members, including the Chair of the Genetics Department at HMS. Based in Boston and launching operations in January 2024, Somite has raised close to $60M to date (Forbes).

Somite’s Core Values:

• We show up – fully accountable, all-in, doing whatever it takes

• We act with urgency – swift, decisive, proactive

• We support one another – collaborative, helpful, empathetic

Location:

Boston, MA (onsite, full-time)

About the Role:

As a Senior Machine Learning Researcher - Biological Foundational Models, you will play a key role in developing foundational models for single-cell RNA sequencing data. Working closely with other machine learning researchers and computational biologists, you’ll design cutting-edge AI solutions, contribute to pioneering research, and help build the core infrastructure driving Somite’s cell-replacement therapy platform. This role is ideal for a machine learning expert driven by scientific inquiry and eager to pioneer biological discoveries through foundational AI models.

Responsibilities:

• Design, train, and optimize foundational models for single-cell RNA sequencing and other high-dimensional omics data

• Collaborate closely with computational biologists to ensure models produce biologically meaningful, interpretable outputs, engaging deeply with biological questions and research

• Design and implement novel deep learning architectures, including transformer-based models tailored to biological data

• Build scalable, distributed pipelines for training and inference across trillion-token biological datasets

• Provide mentorship and technical guidance to other machine learning researchers on the team

Qualifications:

• 6+ years of experience in machine learning, transformer-based deep learning, and large-scale data analysis, preferably in biological applications

• Master’s degree or higher in Computer Science, Artificial Intelligence, Computational Biology, or a related field

• Strong proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow

• Proven experience building and optimizing large-scale models, including transformer-based architectures

• Demonstrated track record of independent research and end-to-end model development, from prototyping to production

• Passion for AI-driven biology and its potential to transform healthcare

Preferred Qualifications:

• Strongly preferred: PhD with a strong publication record in top machine learning and/or computational biology journals

• Strongly preferred: extensive background in biological research and biological modeling, ideally with single-cell RNA sequencing data

• Experience with reinforcement learning (e.g., RLHF, PPO), diffusion models, or multi-modal architectures applied to structured, high-dimensional data

• Experience in startups or fast-paced environments, with a self-directed, proactive work style

Benefits:

• Take a technical leadership role with a mission-driven company with the potential to significantly impact the lives of millions

• Work alongside a talented and passionate team at the forefront of AI and cellular biology

• Contribute to the development of groundbreaking therapies that address s