Overview In this role you will advance agentic AI and multimodal modeling to accelerate oncology discovery and predictive modeling. You will collaborate with research, engineering and pharma partners to design scalable, automated pipelines that leverage foundation models. You'll apply causal inference to large multimodal oncology data and help scale discovery from manual to high-throughput. The work sits at the intersection of LLM orchestration and computational biology, driving impactful R&D insights.
Compensation / Benefits- salary range (CHI: $100,000-$150,000; NYC/SF: $120,000-$160,000)
- incentive compensation
- restricted stock units
- medical benefits
- remote work options
- competitive benefits depending on position
Responsibilities- Develop state-of-the-art agentic workflows and long-horizon planning capabilities
- Build and refine multimodal predictive models using oncology foundation models (DNA, RNA, histology, clinical data)
- Collaborate with clinical scientists and pharma partners to define high-value use cases (e.g., trial design support, treatment de-escalation)
- Contribute to software quality through testing and scalable system design
- Communicate complex technical results to diverse external stakeholders
- Engage in cross-functional collaboration with Research, Engineering & Data Science teams
Key requirements- PhD (or Masters with 3+ years relevant experience)
- Strong AI agent-based workflow experience (e.g., Applied ML, Generative AI, math, biostatistics)
- Biological/medical knowledge and data experience (oncology, RWE, clinical drug development)
- Proficiency in Python and orchestration frameworks (LangGraph preferred)
- Experience building deep agents with state management and graphs
- LLM application skills: prompt engineering, RAG, function calling, evaluating outputs
- Survival analysis expertise (CoxPH, RSF) and oncology model evaluation
- Software engineering practices (unit testing, git) and scalable system design
- Experience with clinical trial or real-world data and emerging RWE methodologies
- Strong communication skills and ability to present to diverse audiences
- Motivation to thrive in a fast-paced environment
- Excellent written and verbal communication
- Collaborative mindset
- Adaptability and prioritization in a fast-paced setting
- Agentic Frameworks: Python, LangGraph or similar
- LLM applications: prompt engineering, RAG, function calling
- Multimodal modeling: integrating DNA, RNA, H&E, and clinical data
