Research Engineer

The role

You will design, prototype, and ship core reasoning and agentic systems. The role involves turning health data into actionable guidance through applied research and product engineering.

What you will do

• Build and iterate on agentic workflows using retrieval, function calling, and planning
• Fine tune and distill models for summarization, extraction, classification, and dialogue
• Develop abstention, routing, and fallback strategies
• Curate high quality datasets from EHR, claims, labs, devices, and chat logs
• Design synthetic data and clinician-in-the-loop labeling pipelines
• Own the eval stack for medical correctness, hallucination, bias, safety, latency, and cost
• Build automated red teaming and regression suites
• Ship research to production with observability, feature flags, and rollback plans
• Optimize inference with batching, quantization, LoRA or QLoRA, and vLLM or TensorRT
• Collaborate with data and product engineers on retrieval, storage schemas, and lineage

Required qualifications

• Strong Python and deep experience with PyTorch or JAX
• Track record shipping applied ML or LLM features to real users
• Hands-on experience with RAG, prompt and tool design, evaluation harnesses, and error analysis
• Solid SQL plus comfort with vector stores and retrieval patterns
• Product sense, pragmatism, and the ability to reduce complex systems into simple, reliable components
• Willingness to work on-site in San Francisco

Nice to have

• Experience with clinical ontologies and standards such as SNOMED CT, ICD, LOINC, RxNorm, FHIR, and NCPDP
• Background in RLHF or RLAIF, distillation, program-of-thought, and structured tool use
• Experience building speech or multimodal pipelines for medical settings
• Contributions to open source, published work, or well known eval frameworks
• Deep familiarity with observability stacks such as Sentry and Langfuse and containerized deployments such as Docker or ECS

About the company

Lotus Health is a primary care app that integrates medical records, AI, and real doctors to provide free, personalized healthcare and prescriptions. The team includes ex-founders and engineers backed by Kleiner Perkins and clinicians at Harvard and Stanford.