Machine Learning Scientist, Applied Machine Learning and Agentic AI, Pharma R&D

Tempus AI•Boston, MA

3d•$120,000 - $160,000•Onsite

About The Position

Tempus is seeking a Machine Learning Scientist specializing in Applied Machine Learning and Agentic AI for their Pharma R&D division in New York, NY. This role is ideal for individuals passionate about precision medicine and advancing healthcare through AI. The company's platform connects real-world evidence to provide actionable insights for physicians, guiding treatment decisions. The Machine Learning Scientist will be instrumental in developing cutting-edge agentic frameworks to automate the discovery of novel prognostic and predictive models in oncology. This position lies at the intersection of advanced Large Language Model (LLM) orchestration and computational biology. The successful candidate will be responsible for building and refining 'deep agents' capable of hypothesis generation, experimental design, and multimodal ML modeling using foundation models. As a key technical contributor, you will collaborate closely with senior scientists and engineers, ensuring code quality and implementing system designs. You will apply advanced scientific methodologies to develop new predictive models and use causal inference frameworks to analyze vast multimodal oncology data, transforming scientific discovery from a manual process into a high-throughput, automated engine.

Requirements

Minimum: PhD (or Masters degree with 3+ years of relevant experience).
Combining: Quantitative and computational skills, specifically in AI agent based workflows (e.g. Applied Machine Learning, Generative AI, Mathematics, biostatistics).
Biological, medical, or drug development knowledge and data (e.g. oncology, RWE, medical science, or clinical drug development).
Agentic Frameworks: Proficiency in Python and orchestration frameworks, specifically LangGraph (strongly preferred) or similar.
Experience building deep agents with complex state management and graphs.
LLM Application: Deep knowledge of prompt engineering, RAG (Retrieval-Augmented Generation), function calling, and evaluating non-deterministic LLM outputs.
Machine Learning: Strong foundation in survival analysis (CoxPH, RSF) and evaluation metrics for oncology models.
Software Engineering: Adherence to software best practices (unit testing, git) and experience designing scalable systems.
Experience working with clinical trial or real-world data, clinical guidelines (e.g., NCCN for oncology) and emerging RWE methodologies
Track record of success: proven in peer reviewed publications or other proven impact.
Communication Skills: Excellent written and verbal communication skills, with the ability to present complex information clearly and persuasively to diverse audiences.
Motivated: Thrive in a fast-paced environment and willing to shift priorities seamlessly.

Nice To Haves

Experience in integrative modeling of multi-modal clinical and omics data, preferably with multimodal embeddings and foundation models.
Strong understanding of data and artificial intelligence in Oncology.
Understanding of cancer biology and clinical data.
Experience with deploying ML models in cloud environments.

Responsibilities

Develop complex, state-of-the-art agentic workflows.
Build agents capable of long-horizon planning, tool use and "co-scientist" reasoning.
Leverage oncology foundation models to integrate DNA, RNA, H&E, and clinical data into predictive algorithms.
Collaborate with clinical scientists and pharma partners to define high-value use cases, such as clinical trial design support and treatment de-escalation.