Principal ML Scientist, Multimodal Biological Reasoning

Flagship Pioneering•Cambridge, MA

About The Position

Pioneering Intelligence builds on Flagship Pioneering’s legacy of founding cutting-edge science and computational ventures, harnessing recent advances in AI, machine learning, and data to accelerate fundamental research and create a portfolio of AI-first companies. As part of Flagship’s integrated model of science, entrepreneurship, and capital, it transforms breakthrough ideas into world-changing companies, elevating the AI advances happening across the ecosystem in human health, sustainability, and beyond. Pioneering Intelligence is seeking a Lead for Flagship's ambitious efforts to build polyintelligent AI systems that unify human scientific expertise, machine intelligence, and nature’s biological signals into multi-modal, multi-scale reasoning engines for biology. As Lead, you will have the unique opportunity to shape our biological reasoning efforts on both the technical and application levels. You will be a hands-on lead for a team of talented machine learning scientists innovating on model architectures that will create best-in-class biological reasoning engines. You will be responsible for sourcing high-value use cases across Flagship and its portfolio companies and translating these into requirements to develop the model towards optimal performance on the unconventional life sciences problems that Flagship tackles. You will work with teams in Pioneering Intelligence and Flagship-at-large to apply our reasoning engines to discover new biology and engineer new biological solutions through massively parallel in-silico reasoning. You will have the opportunity to originate and lead multiple projects in this space over time.

Requirements

PhD, MS, or equivalent experience in computational biology, machine learning, bioengineering, computer science, systems biology, quantitative biology, translational science, or a related field.
Experience in biotech, pharma, AI-for-science, AI drug discovery, venture creation, or a platform organization serving multiple scientific programs.
Experience deploying AI/ML for biology systems into scientific workflows at enterprise scale.
Experience with LLMs, biological foundation models, protein language models, genomic foundation models, scientific agents, or AI discovery platforms.
Experience working across multiple internal and external customers, therapeutic programs, or discovery teams.

Nice To Haves

Industry-leading expertise in modern LLMs, multimodal modeling, representation learning, fine-tuning, post-training, benchmarking, and ML systems.
Deep experience in computational biology, AI-for-biology, AI-enabled drug discovery, translational data science, biological foundation models, or scientific discovery platforms.
Demonstrated ability to work with scientists or biotech teams to scope high-value use cases, identify data assets, define success criteria, and translate discovery needs into technical execution plans.
Working knowledge of biological data modalities such as genomics, transcriptomics, perturbation data, protein sequence, protein structure, pathways, imaging, pathology, or time-series biological data.
Strong judgment around mechanism-of-action reasoning, target discovery, perturbation biology, scientific credibility, model limitations, hallucination risk, interpretability, and validation.
Experience leading small, high-caliber technical teams through ambiguous scientific or product problems.
Ability to communicate clearly with ML researchers, data engineers, portfolio-company scientists, executives, and venture creation leaders.
Comfort operating in an entrepreneurial environment where the goal is not only to build a model, but to create a new capability that can reshape company creation and scientific discovery.

Responsibilities

Own the roadmap: lead the project from architecture and data exploration through model readiness, benchmarking, refinement, and agentic integration.
Guide technical architecture through a biological lens: guide multi-modal, multi-scale model design and ensure the system can ingest and reason over modalities relevant to mechanism-of-action reasoning, target discovery, perturbation biology, pathway reasoning, protein function, and autonomous discovery workflows.
Translate biology into model and evaluation requirements: ensure model development is driven by biological relevance that enables real scientific workflows, not just benchmark performance or technical elegance.
Build the engine for a novel science platform: develop and integrate reasoning engines into Pioneering Intelligence's AI Scientist platform for autonomous science.
Source and shape portfolio use cases: interface with Flagship teams and portfolio company end-users to identify use cases, source data assets, define success criteria, and create end-user feedback loops for reasoning engines that are scientifically meaningful, tractable, and answer high-value questions with real world application.
Communicate the impact: disseminate strategic direction and scientific results to Flagship stakeholders and in public forums.