L

Lumos AI Research

Data infrastructure for health AI safety

Clinical Project Lead

Medical, Clinical & VeterinaryPosted on Nov 13
Full-timeSan Francisco, CA, USA$180k - $200k /yr

About the Job

Requirements

  • An MD or DO from an accredited program and completed United States residency in Internal Medicine, Family Medicine, or Cardiology.
  • United States board certification in Internal Medicine (ABIM or AOBIM), Cardiovascular Disease (ABIM) following fellowship, or Family Medicine (ABFM or AOBFP).
  • At least 3 years of post-residency or post-fellowship clinical experience, with recent or active clinical practice.
  • Strong command of evidence-based medicine, guideline-concordant care, and clinical reasoning under uncertainty.
  • Comfort working with structured clinical data and electronic health record concepts, and willingness to work closely with engineers and researchers.
  • Rigor about correctness, reproducibility, and edge cases.
  • Excellent written and spoken communication.
  • Candidates must be authorized to work in the United States without sponsorship.

Responsibilities

  • Build gold-standard, expert-annotated clinical cases and reference solutions across internal medicine, cardiology, and primary care, including diagnosis and differential reasoning, triage and risk stratification, chest pain and acute coronary syndrome workups, heart failure and arrhythmia management, electrocardiogram and cardiac test interpretation, longitudinal management, medication reconciliation, guideline-concordant care, and clinical documentation using realistic patient data such as FHIR bundles and structured electronic health records.
  • Review and adjudicate work from a network of physician experts, and own the clinical quality bar, scoring rubrics, and inter-rater reliability.
  • Design and ship reinforcement learning environments and verifiers for clinical agents with the research and engineering team, translating correctness and safety criteria into automated signals.
  • Stress-test and red-team models on clinical tasks, identify hallucinations, missed red flags, and unsafe guidance, and turn failures into lasting evaluations.
  • Serve as the clinical voice with customers and the physician expert network, helping recruit and calibrate that network.

Desired Qualifications

  • Hands-on experience using artificial intelligence tools in clinical practice, such as ambient AI scribes and documentation assistants, large language model-based clinical decision support, AI-assisted electrocardiogram or imaging interpretation, electronic health record-embedded AI features, or general-purpose large language models for clinical reasoning.
  • Prior experience annotating, evaluating, or red-teaming clinical artificial intelligence or large language model systems.
  • Experience writing clinical guidelines, quality measures, or board-style assessment content, such as ABIM, ABFM, or MKSAP-style questions.
  • Publications in clinical medicine, evidence-based medicine, cardiology, or medical AI.
  • Exposure to reinforcement learning, verifier-based scoring, or evaluation frameworks.

About the Company

Lumos AI Research

Data infrastructure for health AI safety

Lumos AI Research builds data infrastructure to improve AI model accuracy and safety for health and life sciences. It partners with labs, startups, and governments and has supported major tech firms like OpenAI, Google, and Meta. Its offerings center on data-centric AI methods including Supervised Fine-Tuning (SFT) with high-quality prompt-response examples, Reinforcement Learning with Human Feedback (RL/HF) guided by medical experts, Preference Ranking, and Reinforcement Learning from AI Feedback (RLAIF). It also develops Health RL simulation loops and uses Traces to teach AI agents from user actions. The company differentiates itself through a focus on high-stakes health data, a team with backgrounds from OpenAI, Scale, TikTok, MIT, and Harvard, and its role as a partner for training and evaluating models in regulated environments. Its goal is to help organizations build, train, and evaluate safer, more accurate AI systems for health and life sciences.

Company size
11-50
Company stage
Not listed
Total funding
Not listed
Headquarters
San Francisco, CA
Founded
2025

Recently Posted Jobs

Explore more opportunities at Lumos AI Research

See more jobs