Atria Institute

Atria Institute

Atria—Turning science into medicine. Atria takes a scientific approach to preventive medicine, precision longevity medicine, and proactive health care. Atria Palm Beach at The Royal Poinciana Plaza Coming Early 2024 561.200.7000 The future of health br...

Health Care Providers & Services
51-250
Founded 2022

Description

  • Own the medical modeling roadmap and build models that improve clinical outcomes for Atria's use cases.
  • Survey open-source and clinical/biomedical foundation models and recommend what to fine-tune, distill, or build on.
  • Design and validate novel model architectures for longitudinal multimodal data when existing approaches are insufficient.
  • Lead fine-tuning and post-training workflows including SFT, LoRA/QLoRA, DPO, RLHF/RLAIF, continued pre-training, and distillation.
  • Curate high-quality training datasets from clinical data, including sampling, labeling, deduplication, contamination checks, and PHI-safe handling.
  • Design and run rigorous model evaluation, including held-out benchmarks, calibration analysis, subgroup performance, and ablations.
  • Train and evaluate models on single-node and multi-GPU infrastructure with strong experiment tracking and reproducible configuration management.
  • Stay current on relevant research in training methods, fine-tuning techniques, medical foundation models, and multimodal architectures.
  • Collaborate with clinicians to define model quality and with research partners on joint training and evaluation.

Requirements

  • A graduate degree in computer science, machine learning, computational biology, biomedical informatics, or a closely related field, or a strong open-source track record in modern training and fine-tuning.
  • PhD preferred; Master's degree accepted with a strong research record.
  • 4+ years of hands-on experience training and fine-tuning modern deep learning models, with shipped or published models personally trained.
  • Deep, current fluency with SFT, PEFT methods such as LoRA, QLoRA, and adapters, preference tuning such as DPO and successors, distillation, and continued pre-training.
  • Strong working knowledge of the open-source model ecosystem and what is worth fine-tuning for a given problem.
  • Strong Python and PyTorch skills, with hands-on experience using the Hugging Face ecosystem or equivalent training stacks.
  • Practical experience with distributed training, mixed precision, efficient data loading, and experiment tracking tools such as W&B or MLflow.
  • Discipline around evaluation and ablation, including benchmarking and calibration analysis.
  • A bias toward shipping models over writing papers, and the ability to move quickly from idea to working experiment.
  • A genuine interest in healthcare and the responsibility of building models that affect patient care.
  • Experience building multimodal medical models combining text, imaging, structured labs, or physiological signals is preferred.
  • Familiarity with clinical or biomedical foundation models such as Med-PaLM, MedGemma, BioMedLM, BiomedCLIP, or RadFM is preferred.
  • Peer-reviewed publications in ML, NLP, computer vision, or clinical informatics venues are preferred.
  • Experience with reinforcement learning, reasoning model training, or other frontier post-training techniques is preferred.
  • Experience with model interpretability and uncertainty quantification for clinical settings is preferred.
  • Prior collaboration with clinicians on models that shipped is preferred.

Benefits

  • Excellent health and wellness benefits fully covered by Atria սկսing on the date of hire.
  • OneMedical membership for employees and dependents with access to 24/7 virtual care.
  • Fertility and family planning support.
  • Company-covered preventive health screenings through partner hospitals.
  • Fitness perks, including Wellhub+.
  • 401(k) contributions with a 4% company match starting after 6 months.
  • Flexible Time Off.
  • Continuing medical education and CEU support for professional licensure.
  • Base salary of $180,000 to $260,000 plus a performance-based bonus.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

RL Environment Software Engineer

Talentpluto, Inc. 1-10 Recruiting

An applied AI research lab is hiring a remote RL Environment Software Engineer to build reinforcement-learning environments and agents for real-world workflows as the company expands into new domains.

Docker Kubernetes Machine Learning Node.js Python React Reinforcement Learning TypeScript
16 hours, 23 minutes ago

Generative AI Research Intern

Appier 251-1K Professional Services

Appier is hiring a Research Scientist to advance generative and agentic AI research for LLMs, VLMs, and autonomous systems that can be turned into production products.

Generative AI LLM Python PyTorch Reinforcement Learning
16 hours, 38 minutes ago

PhD Studentship: Causal Reinforcement Learning

Phaidra 51-250 Internet Software & Services

Phaidra is offering a fully funded 4-year PhD studentship with the University of Cambridge to research causal inference and reinforcement learning for robust AI control systems in industrial and data centre environments.

Machine Learning NumPy Python PyTorch Reinforcement Learning Scikit-learn SciPy
2 days, 16 hours ago

RL Environment Software Engineer

Talentpluto, Inc. 1-10 Recruiting

A remote RL Environment Software Engineer at an applied AI research lab building reinforcement-learning environments and agents for leading AI labs, with the goal of creating high-quality systems the frontier will need next.

Docker Kubernetes Machine Learning Node.js Python React Reinforcement Learning TypeScript
3 days, 16 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers