Atria Health and Research Institute

Role Description As a Senior Data Scientist at Atria, you will generate the medical insights and forecasts that shape how our clinicians care for members and how Atria runs as a practice. You'll work with one of the most distinctive longitudinal datasets in medicine: deep per-member baselines (whole-genome sequencing, advanced imaging, comprehensive labs, movement analysis, lifestyle inputs) revisited on cadence over years and linked across full family lineages, alongside the operational data of how a multi-disciplinary care team actually delivers that care. Your work spans both sides of that equation: surfacing clinically meaningful patterns clinicians can act on, and building the analyses, forecasts, and operational models that help Atria deliver better care more efficiently. What you'll do - Generate medical insights from Atria's longitudinal clinical data: surface early signals of disease, characterize how members respond to interventions, and identify population-level trends clinicians can act on. - Build forecasting models on clinical and operational signals: disease progression, biomarker trajectories, member engagement, demand and capacity planning, and other time-series problems. - Lead or contribute to operational analytics: visit patterns, throughput and scheduling, panel composition, vendor performance, member journeys, and the quiet efficiency questions that compound over a year. - Design and execute studies in partnership with clinicians: clear questions, well-controlled comparisons, honest error analysis, and writeups that hold up to clinical scrutiny. - Design and analyze experiments (A/B tests, staged rollouts, quasi-experiments) with appropriate attention to power, multiple comparisons, and the difference between "statistically significant" and "actually mattered". - Author and maintain curated views and dbt models in our Snowflake gold layer, documented well enough that clinicians and operational staff can use them confidently without a Slack DM to you every Tuesday. - Build dashboards and analytical tools in Omni Analytics that clinicians and operational leaders actually use to make decisions. - Partner with the AI Scientists and AI Engineers on the boundary where analytical work meets model training and production systems: contributing ground truth, evaluation datasets, and the clinical framing that keeps their models pointed at the right problem. - Translate clinical and operational questions into well-formed analytical problems, and translate results back into clear recommendations. The translation in both directions is most of the job. - A bias to deliver. You would rather have a clear answer to a real question in front of a clinician next week than a beautiful methodology that ships next quarter. - A scrappy streak. You can pick up an unfamiliar dataset, statistical method, or clinical concept on a Wednesday and have a credible first cut by Friday. - A serious drive to keep getting better. You read other people's analyses, papers, and code. You treat being wrong as cheap information rather than an event requiring counseling. Qualifications - Experience in data science, analytics, or applied statistics: 5+ years, with at least 2 in healthcare, biomedical, or another regulated longitudinal-data domain. - Strong foundation in statistics and probability: you can defend a confidence interval, a regression specification, and a sensible forecasting baseline honestly. - Solid working knowledge of forecasting and time-series methods (classical and modern), regression modeling, and applied ML for tabular data (gradient boosting and related). - Familiarity with the design and analysis of experiments and quasi-experiments: enough to know when an A/B test is the right tool, when it isn't, and what to do about it. - Strong Python (pandas, scikit-learn, statsmodels, and at least one forecasting library) and SQL that you write without apologizing for. - Comfort with a cloud warehouse (Snowflake preferred) and modern data tooling such as dbt and a workflow orchestrator (Dagster, Airflow). - Track record of partnering with domain experts and turning their questions into defensible analytical work: clinicians, ops leaders, or comparable stakeholders. - Clear written and visual communication: tight executive summaries, defensible methods sections, and charts that have titles, axes, and a point. - Interest in healthcare and the responsibility that comes with working on data that affects patient care. Nice to have - Graduate degree in a quantitative field (statistics, biostatistics, epidemiology, computer science, applied math, or a relevant clinical/biological science), or a strong track record of analytical work in lieu of formal credentials. - Experience with causal inference methods. - Experience with modern forecasting toolkits and hierarchical or probabilistic forecasting. - Familiarity with modern deep learning tools (PyTorch, Hugging Face ecosystem): enough to collaborate productively with AI Scientists and Engineers. - Familiarity with a BI tool (Omni, Looker, Mode, Tableau). - Published peer-reviewed clinical, biomedical, or operations research. - Any prior work in healthcare, biology, or another regulated domain. Salary $180,000 - $260,000 Base Salary + performance-based bonus Benefits - Excellent health and wellness benefits, fully covered by Atria, effective date of hire. - OneMedical membership for employees & dependents, giving access to 24/7 virtual care. - Fertility & family planning. - Company-covered preventive health screenings through partner hospitals (calcium score). - Fitness Perks, including Wellhub +. - 401k contributions and 4% match starting after 6 months.

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.

Role Description As a Senior AI Engineer at Atria, you will own the design, development, and production deployment of the LLM-powered systems that put AI directly in front of clinicians and members: - Agentic medical companions - Clinical decision support - Document understanding pipelines that turn unstructured clinical data into usable signal This is a hands-on, high-ownership role for an engineer who wants to do work with direct patient impact. What you'll do - Architect and ship production AI systems end-to-end (orchestration, retrieval, inference, evaluation, and monitoring) for clinical decision support, document understanding, and agentic medical companions. - Design agentic workflows with custom skills and harnesses, using frontier LLMs and self-hosted models where appropriate. - Lead development of structured information extraction pipelines from clinical documents, including automated verification systems and human-in-the-loop gates, where necessary. - Build robust evaluation infrastructure (golden datasets, LLM-as-judge, regression tests, online A/B evaluation) that gates every model and prompt change. - Engineer for latency and cost: streaming, caching, prompt compression, model routing, and inference-cost budgets. - Own production health: trace- and span-level observability, prompt versioning, drift detection, cost monitoring, replay-from-production for debugging, PHI-safe logging throughout. - Operationalize models trained by the AI Scientist team: serving, evaluation in production, rollback paths, and feedback loops that turn real usage into training and eval data. - Partner with clinicians, the data engineering team, and research collaborators to translate clinical requirements into specifications and deliverable systems. - Educate and mentor PMs and engineers across Atria on applied AI best practices. Leadership and Influence - Set technical direction for AI engineering at Atria: architecture decisions, build-vs-buy calls, and evaluation and observability standards. - Raise the bar on engineering practices, code review, observability, and incident response. - Drive vendor and partner technical due diligence for AI/ML vendors: BAA scope, PHI handling, sub-processor obligations, and IP terms. - Mentor other AI engineers through code review, design docs, and architecture decisions. - A bias to ship: prefer a rough thing in production tomorrow over a beautiful thing in a design doc next quarter. - A scrappy streak: pick up an unfamiliar tool, framework, or clinical concept quickly. - A serious drive to keep getting better: read others' code, papers, and post-mortems. Qualifications - Hands-on experience building and operating LLM-powered or production ML systems: 4+ years. - Strong Python skills and deep familiarity with at least one production backend framework (FastAPI, Flask, etc.). - Hands-on experience with LLM orchestration, function/tool calling, and retrieval system design. - Working knowledge of a cloud data warehouse (Snowflake strongly preferred) and modern data tooling such as dbt, Dagster, or Airflow. - A track record of designing evaluation systems for LLM applications. - Familiarity with safety considerations for LLM applications. - Practical understanding of HIPAA, BAAs, PHI handling, and working in a regulated environment. - Strong written communication: design docs, technical RFCs, and documentation. Nice to have - Experience in healthcare, clinical informatics, or other regulated domains. - Familiarity with medical ontologies (LOINC, SNOMED CT, ICD-10, RxNorm) and clinical data standards (FHIR, HL7). - Experience with self-hosted model serving and inference optimization. - Multimodal experience: vision, structured data, or time-series data alongside text. Salary and Benefits - Salary range: $190,000 - $250,000 + performance-based bonus - Excellent health and wellness benefits, fully covered by Atria, effective date of hire - OneMedical membership for employees & dependents, giving access to 24/7 virtual care - Fertility & family planning - 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