• Act as the voice of the buyside customer and run regular user sessions to shape and execute AI product strategies that directly address user needs and business goals. • Work side-by-side with engineering, design, and product marketing to build, launch, and optimize innovative AI-first solutions tailored to our customers. • Analyze market trends, emerging AI capabilities, and competitor moves to identify where we can leap ahead. • Lead the end-to-end product development lifecycle, from ideation and experimentation through to launch, post-launch analysis, and iteration.

• Own the medical modeling roadmap at Atria: identify the model families and training approaches most likely to win on our problems, and build the models that prove it. The bar is "moves the clinical needle", not "places on a leaderboard". • Survey the open-source landscape (general-purpose and clinical/biomedical foundation models, vision and multimodal backbones, specialized medical models) and make defensible recommendations on what to fine-tune, distill, or build on. • Design and validate novel architectures where existing approaches fall short, particularly for longitudinal multi-modal data and the foundation-model direction. • Lead fine-tuning and post-training work: SFT, LoRA/QLoRA and other PEFT methods, DPO and related preference-tuning approaches, RLHF/RLAIF where appropriate, continued pre-training, and distillation. • Curate high-quality training datasets from Atria's clinical data: sampling, labeling strategy, deduplication, contamination checks, train/test hygiene, and PHI-safe handling throughout. • Design and run rigorous evaluation: held-out clinical benchmarks, comparison against frontier closed-source baselines, calibration analysis, subgroup performance, and the ablations that tell you which design choices actually earned their keep. • Run training and evaluation on appropriate infrastructure (single-node and multi-GPU), with proper experiment tracking, reproducible configs, and the kind of logging that lets your future self understand what your past self did. • Stay current with the literature: training methods, fine-tuning techniques, medical foundation models, multimodal architectures. Synthesize what's actually relevant for Atria rather than reporting every new arXiv preprint as a strategic threat. • Collaborate with clinicians on what "good" looks like for each model, and with research partners on joint training and evaluation work.

Role Description As a Senior AI Scientist at Atria, you will own the development of the medical models at the heart of Atria's clinical AI agenda: - Domain-specific models for clinical problems that matter most to our practice today. - Foundation models for preventive medicine that learn underlying patterns of health evolution. - Access to a unique data estate including whole-genome sequencing, advanced imaging, and family-linked records. Your core job is to take the best of what the open-source ecosystem has to offer and turn it into models that materially outperform off-the-shelf options on Atria's problems. What you'll do - Own the medical modeling roadmap at Atria: identify model families and training approaches. - Survey the open-source landscape and make defensible recommendations on fine-tuning or building models. - Design and validate novel architectures for longitudinal multi-modal data. - Lead fine-tuning and post-training work: SFT, LoRA/QLoRA, DPO, RLHF/RLAIF, continued pre-training, and distillation. - Curate high-quality training datasets from Atria's clinical data. - Design and run rigorous evaluations: held-out clinical benchmarks, calibration analysis, subgroup performance. - Run training and evaluation on appropriate infrastructure with proper experiment tracking. - Stay current with literature relevant to Atria's needs. - Collaborate with clinicians and research partners on model evaluation and training. What you'll bring - A bias toward shipping models rather than papers. - A scrappy streak: ability to quickly learn unfamiliar techniques and concepts. - A serious drive to keep improving and learning from others. - Graduate degree (PhD preferred) in a relevant field or strong open-source track record. - Hands-on experience training and fine-tuning deep learning models (4+ years). - Deep fluency with modern fine-tuning and post-training methods. - Strong working knowledge of the open-source model ecosystem. - Strong Python and PyTorch skills, with experience in the Hugging Face ecosystem. - Practical experience with training infrastructure. - Discipline around evaluation and ablation in modeling work. - Genuine interest in healthcare and its responsibilities. Nice to have - Experience building multimodal medical models. - Familiarity with clinical/biomedical foundation models. - Peer-reviewed publications in relevant fields. - Experience with reinforcement learning and frontier post-training techniques. - Experience with model interpretability and uncertainty quantification. - Prior collaboration with clinicians on models that shipped. Salary and Benefits - Salary range: $180,000 - $260,000 base salary + performance-based bonus. - Excellent health and wellness benefits, fully covered by Atria, effective date of hire. - OneMedical membership for employees & dependents, providing access to 24/7 virtual care. - Fertility & family planning support. - Company-covered preventive health screenings through partner hospitals. - Fitness Perks, including Wellhub +. - 401k contributions and 4% match starting after 6 months. - Flexible Time Off. - Continuing medical education (CME) and CEU support for professional licensure.

• Research • Development of a memory framework process • Article writing • Patent submission