SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 140,000 - 210,000 / annual
Tempus is seeking a Senior Scientist in Applied Machine Learning and Generative AI to advance its precision medicine platform. The role focuses on developing sophisticated computational analyses, algorithms, causal models, and agent-based tools that support pharmaceutical R&D by leveraging Tempus' proprietary platform connecting real-world evidence to deliver actionable clinical insights.
Key Responsibilities:
- Perform complex computational analyses and develop machine learning algorithms, causal inference models, and generative AI tools to enhance the Tempus platform for drug R&D
- Become an expert in Tempus' multimodal patient datasets (epidemiological, clinical, genomic, transcriptomic, and pathology imaging data)
- Drive continual platform improvement by championing new ML and generative AI capabilities aligned with client needs and industry trends
- Collaborate across Research, Engineering, and Data Science teams to develop and deliver innovative computational solutions
- Co-develop solutions with pharmaceutical partner science and clinical teams
- Gain proficiency in pharma strategies, drug modalities, and pipelines to identify where the platform adds value
- Extract and communicate impactful insights to diverse stakeholders, including external pharma partners
- Provide scientific leadership and mentoring to computational biologists and RWE scientists, guiding AI tool adoption
- Stay current with industry trends, best practices, and advancements in machine learning and AI
Requirements:
- Minimum PhD or Master's degree with 2+ years of relevant experience, plus an additional 2+ years of relevant industry or post-doctoral experience
- Proficiency in R, Python, and SQL
- Deep expertise in causal AI, causal inference, and/or explainable AI (e.g., Causal Machine Learning, Directed Acyclic Graphs, counterfactual reasoning, heterogeneous treatment effect estimation)
- Hands-on experience with agentic orchestration frameworks (e.g., LangChain, LangGraph, AutoGen, DSPy)
- Strong knowledge of LLM-driven agent architectures, including prompt engineering, RAG (Retrieval-Augmented Generation), and function calling/tool use
- Deep knowledge of machine learning and statistical modeling
- Biological, medical, or drug development knowledge and data (e.g., oncology, RWE, medical science, clinical drug development)
- Awareness of machine learning applications in molecular/biomedical data analysis or drug discovery/development
- Track record of success demonstrated through peer-reviewed publications
- Excellent written and verbal communication skills with ability to present complex information clearly to diverse audiences
- Comfort in client-facing roles and ability to deliver technical training internally and externally
- Ability to thrive in fast-paced environments and shift priorities seamlessly
Preferred:
- Experience in integrative modeling of multi-modal clinical and omics data
- Strong understanding of data and AI in drug R&D
- Understanding of cancer biology
- Previous experience with large transcriptome and NGS datasets, or clinical/real-world medical data
