Principal ML Engineer

Principal ML Engineer 

We’re looking for a Principal Machine Learning Engineer to lead the implementation of advanced AI models across the clinical and genomics applications. This role is ideal for someone who is both highly technical and impact-driven - focused on rapidly building, deploying, and iterating on models that drive real-world results in precision medicine. You’ll be at the frontier of clinical AI, working with real-world patient data to build systems that power precision medicine, from cancer care to reproductive health.

Responsibilities

• Model Selection, Tuning and Deployment

  • Identify and evaluate best-fit models for a wide range of tasks (e.g., clinical entity recognition, summarization, variant interpretation, workflow automation).

  • Fine-tune or optimize foundation models (LLMs, transformer, etc.) for targeted clinical/genomic outcomes.

  • Design for scalability, observability, and maintainability in ML deployments.

  • Package and serve models for production inference (REST APIs, batch pipelines, or real-time services).

• Agent and Workflow Development

  • Build agentic systems that can answer complex clinical or genomic queries.

  • Automate human-in-the-loop workflows for expert-level decision support.

  • Navigating longitudinal patient records for best practice recommendation and decision support.

  • Integrate external tools, databases, or domain-specific knowledge into agentic pipelines.

• Iteration and Evaluation

  • Rapidly test hypotheses and ship prototypes or MVPs in collaboration with product team.

  • Define and track evaluation metrics (e.g., extraction accuracy, latency, alignment with ground truth).

  • Collaborate with ML scientists, clinicians, bioinformaticians, product and other cross-functional stakeholders to align technical implementation with real-world constraints.

• Engineering and Collaboration

  • Own the ML engineering stack, from model integration and experimentation to cloud-native deployment.

  • Contribute to a reusable foundation of tools (prompt libraries, feature extractors, evaluation harnesses, etc.).

  • Work with company-wide vector store and document mesh infrastructure to design and optimize high-performance retrieval strategies for LLM pipelines.

  • Partner with AI, data, platform, and product pods to deliver production-ready features on a complex and evolving platform.

  • Security and compliance: Ensure all model pipelines adhere to data governance, privacy, and compliance standards in healthcare and genomics

​Requirements

• PhD in Computer Science, Computational Biology, Bioinformatics, Statistics, or related field, or equivalent practical experience.

• 8+ years of experience applying machine learning to real-world problems, preferably in healthcare or genomics domains.

• Proficiency in deep learning frameworks such as PyTorch, TensorFlow, or Keras. 

• Experience with integrating LLMs (e.g., OpenAI, LLaMA, DeepSeek, Claude) into downstream clinical workflows.

• Expertise in fine-tuning and optimizing pre-trained models for domain-specific applications.

• Familiarity with agent frameworks (e.g., LangChain, Haystack,  ReAct) and retrieval-augmented generation (RAG) techniques.

• Experience with semantic search, hybrid search, and vector databases.

• Strong programming skills in Python; familiarity with libraries such as scikit-learn, pandas, and NumPy.

• Experience with containerization (Docker) and orchestration (Kubernetes).

• Knowledge of API development and integration, including RESTful services.

• Experience with cloud platforms (AWS, Azure, or GCP) and associated ML services.