Scientist, Machine Learning (Large Language Models for Materials)

Flagship Pioneering - Cambridge, MA

Full-time - Entry Level

Cambridge, MA

Professional, Scientific, and Technical Services

About the position

The Scientist, Machine Learning position at Flagship Labs 97 Inc. focuses on leveraging large language models (LLMs) to enhance materials discovery and development. The role involves fine-tuning and deploying LLMs for knowledge extraction from scientific literature, collaborating with computational and experimental teams, and contributing to a digital platform for continuous model improvement. The ideal candidate will thrive in a collaborative, innovative environment and will be instrumental in driving advancements in materials science through AI.

Responsibilities

• Fine-tune, scale and deploy large language models over scientific and patent literature for knowledge extraction in materials synthesis and performance.
• Utilize and develop new prompt engineering strategies in the materials domain.
• Use LLM-backed agents for lab orchestration, design of experimental assays, and optimization of process parameters for materials synthesis and testing.
• Contribute to a digital platform that can continually finetune models as more data becomes available.
• Continually cultivate scientific/technical expertise through critical review of ML literature, attending conferences, writing publications, and developing relationships with key opinion leaders.
• Work with the computational team to identify materials design pathways that target desired functional properties and their synthesis.
• Work with the experimental team to drive material discovery and development.
• Report findings to stakeholders and leadership in written reports and verbal presentations.

Requirements

• PhD in Computer Science, Applied Mathematics, quantitative disciplines with strong focus in ML, or related field.
• Coding experience with large language models (e.g. GPT or other autoregressive LLMs).
• Strong experience with prompt engineering.
• Hands-on experience implementing, deploying, evaluating, fine-tuning and hyperparameter-tuning deep learning models at scale.
• Experience in machine learning strategies like lifelong learning, online learning, incremental learning.
• Strong experience in at least one ML framework (PyTorch/TensorFlow/Jax) and robust experience in Python data science ecosystem (Numpy, SciPy, Pandas, etc.).
• Experience using a cloud computing service to reduce runtime to train and evaluate deep learning models.
• Strong self-starter and independent thinker, with strong attention to detail.
• Demonstrated industry experience or academic achievement.
• Excellent communication and presentation skills, capable of conveying technical information in a clear and thorough manner.

Nice-to-haves

• Experience using AWS services.
• Experience with machine learning integration in experiment workflows.

Benefits

• Opportunity to work in a mission-driven team.
• Collaborative and innovative work environment.
• Access to professional development opportunities.