ML Postdoc Researcher - Healthcare AI Innovation

Truveta is transforming healthcare by enabling researchers, clinicians, and life sciences organizations to learn from one of the most comprehensive collections of de-identified patient data in the United States. We are seeking a highly motivated Postdoctoral Researcher to explore and develop novel applications of cutting-edge AI/ML technologies on large-scale real-world clinical data. This role is designed for recent PhD graduates who are passionate about pushing the boundaries of machine learning in healthcare. You will work at the intersection of machine learning, clinical data, and biomedical science, identifying new opportunities where modern AI can unlock insights that were previously out of reach. A key expectation is not just execution—but imagination: the ability to envision and prototype entirely new ways to use rich patient data to solve meaningful healthcare problems.

Responsibilities

Innovate: Identify and propose novel, high-impact applications of AI/ML using large-scale EHR data; Research & Prototype: Design, develop, and evaluate state-of-the-art models (e.g., foundation models, multimodal learning, causal ML, generative AI); Work Across Modalities: Integrate structured and unstructured EHR data with emerging data types such as genomics, imaging, and clinical notes; Collaborate Cross-Functionally: Partner with clinicians, data scientists, and product teams to translate research ideas into real-world solutions; Publish & Share: Contribute to top-tier conferences/journals and represent Truveta in the research community; Explore the Unknown: Proactively identify problems that have not yet been addressed and define new research directions

Requirements

Recent PhD graduates; Curious and imaginative; Impact-driven; Comfortable with ambiguity; Collaborative; Collaborate with researchers and engineers to design, develop, and refine large language models and generative models for various applications; Utilize your expertise in machine learning and natural language processing to develop novel algorithms and methodologies for generative modeling tasks; Implement, train, and fine-tune LLM and GPT-like models on large-scale datasets to ensure optimal performance and accuracy; Stay up to date with the latest research advancements and techniques in the field of language modeling, generative modeling, and machine learning; Deliver the next generation of innovation in trustworthy healthcare; Physically present in the United States for the duration of the program

Nice to have

Experience with healthcare data (EHRs, claims, clinical notes) or biomedical data (genomics, imaging); Familiarity with cutting-edge areas such as: Foundation models / LLMs in healthcare; Multimodal learning; Causal inference; Representation learning on longitudinal data; Track record of publications in top-tier ML or healthcare venues (e.g., NeurIPS, ICML, ICLR, MLHC, AMIA); Ability to work across disciplines and communicate with both technical and clinical stakeholders

Benefits

Competitive compensation; Company-issued laptop and equipment; Opportunities for future full-time positions