MyOme is looking to leverage AI/ML to design LLM-powered agents, RAG pipelines, and predictive models that safely and effectively use clinical and genomic data to accelerate product development across multiple disease areas, expand clinical AI solutions into new therapeutic domains, reduce time-to-market for new features, and enable scalable personalization for providers and patients.
Requirements
- Proficiency in Python and ML frameworks (PyTorch/TensorFlow); strong software engineering fundamentals.
- Hands-on with LLMs development and fine-tuning, prompt design, function/tool calling, RAG, and vector databases (FAISS, Pinecone, Weaviate).
- Experience with AI agent frameworks (LangChain, LangGraph, CrewAI, AutoGen) and building multi-step or multi-agent workflows.
- Strong SQL; experience with distributed data processing (e.g., Spark/Databricks)
- Familiarity with healthcare data standards (HL7 FHIR, OMOP; SNOMED CT, ICD-10/11, LOINC, RxNorm) and their use in ML/RAG pipelines.
- Understanding of HIPAA/GDPR, PHI handling, encryption, RBAC, and audit logging in production systems.
- Genomic data experience; clinical NLP; speech-to-tech; LoRA/PEFT fine-tuning; RHLF/RLAIF; federated learning, imaging models.
Responsibilities
- Design and implement agentic systems
- Build RAG pipelines that ground LLMs in curated, up-to-date medical knowledge and EHR data
- Develop, test, and version prompts and tool-use workflows
- Integrate tool calling and APIs
- Integrate and improve existing disease-risk and polygenic risk workflows using features derived from structured EHR, clinical notes, labs, and (as needed) imaging.
- Apply NLP for clinical text, entity/ontology mapping, and embedding strategies.
- Establish CI/CD, model and prompt registries, feature stores, and reproducible training/inference pipelines.
Other
- This will be an onsite position at our Menlo Park, CA location.
- Work cross-functionally (engineering, product, clinical, lab, research) to define requirements, timelines, and success metrics.
- Share progress transparently; surface risks early; contribute to best practices in healthcare AI engineering.
- PhD in CS, EE, Bioinformatics, or a related field; OR 5+ years of industry ML experience.
