Atria Institute

• 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.

• 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, and resisting the urge to reach for an agent when a function call would do. • 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. Accuracy, safety, cost, and latency are first-class metrics. • 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, and the general art of finding out something is broken before a clinician does. • Operationalize models trained by the AI Scientist team: serving, evaluation in production, rollback paths, and the feedback loops that turn real usage into training and eval data, rather than into a Slack thread nobody reads. • Partner with clinicians, the data engineering team, and our research collaborators to translate clinical requirements into specifications and deliverable systems. • Educate and mentor PMs and engineers across Atria on applied AI best practices, from prompt and evaluation design to choosing the right model for the job (which, surprisingly often, is not the largest one). • Set technical direction for AI engineering at Atria: architecture decisions, build-vs-buy calls, and the evaluation and observability standards the team actually works to. • Raise the bar on engineering practices, code review, observability, and incident response. Quietly, persistently, and with grace. • 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, with the patient conviction that good systems are made twice: once badly, then properly.

• 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.

• Identify the highest-leverage opportunities for agentic systems and emerging technologies across Product, Design, and Engineering workflows • Map end-to-end workflows and turn ambiguous opportunities into clear technical strategies and phased execution plans • Prioritize work based on measurable business value, technical feasibility, operational risk, and adoption potential • Help Atria stay current on meaningful advances in emerging technologies and translate them into practical plans • Architect and build Atria’s internal platforms for agentic workflows, including context retrieval, integrations, permissions, validation, observability, and auditability • Design reusable services, APIs, patterns, and interfaces that support AI-assisted workflows across planning, implementation, review, release, and incident response • Build and ship high-impact workflow improvements yourself, especially in the highest-priority and most technically challenging areas • Create systems that can safely combine context across code, documentation, design files, collaboration tools, analytics, and other internal sources • Define integration patterns that allow new workflows to be added without rebuilding core primitives every time • Establish evaluation frameworks for agentic systems • Define how output quality is measured and how systems are monitored over time for drift, regressions, and operational failures • Instrument workflows with meaningful metrics tied to adoption, cycle time, review efficiency, quality, reliability, and user trust • Partner with Foundations Engineering and other stakeholders to implement appropriate controls around permissions, access, audit trails, vendor risk, and sensitive data handling • Define where agents can act autonomously, where human approval is required, and how those boundaries are enforced in tooling • Create playbooks, standards, and training that help engineers, product managers, and designers adopt effective AI-assisted ways of working • Raise the bar on internal practices around context management, prompt and workflow design, evaluation, and safe rollout • Serve as a trusted technical leader across teams, influencing direction through strong judgment, credibility, and hands-on execution • Mentor engineers through design guidance, implementation partnership, and thoughtful code review • Help teams distinguish between impressive demos and durable production systems

• Define, champion, and evolve a multi-year design vision and strategy for the Atria experience, in alignment with company goals and product roadmap. • Serve as the principal design voice in strategic conversations, influencing at all levels of the organization. • Advocate for a member-first approach, ensuring high craft, empathy, and precise attention to detail in all design decisions. • Lead design for high-impact initiatives, from concept to launch, across multiple platforms and touchpoints. • Design quality significantly exceeds that typically found in healthcare and matches the high-touch, luxury physical experience provided at the Atria Institute. • Evolve Atria's design system into a world-class language, ensuring scalability and brand consistency across all member-facing products • Integrate service design thinking to connect digital and physical member experiences. • Drive the use of qualitative and quantitative insights to inform design decisions. • Identify emerging trends and technologies in design, health tech, and consumer experiences, applying them to push Atria’s work forward. • Conduct UX research to validate and iterate on concepts, ensuring measurable impact on member satisfaction and engagement. • Partner closely with peers in product, design, data, and engineering to align design direction with broader strategic goals. • Influence and drive alignment across multidisciplinary stakeholders • Establish and track design KPIs tied to member engagement, retention, and satisfaction in collaboration with product partners • Continuously refine the design process to improve speed, quality, and collaboration.

About Atria Atria is a membership-based preventive health care practice delivering cutting-edge primary and specialty care from the comfort of your home, at our practices in Palm Beach and New York, or wherever you are in the world. We bring together a multidisciplinary team of renowned, in-house physicians to provide proactive, preventive, and precision-based care for Atria members and their families. We aim to optimize the lifespan and healthspan of all our members through meticulous screening and tailored interventions to prevent, reverse, or manage all major chronic diseases. Each member’s care is led by a dedicated Chief Medical Officer who collaborates on your behalf with specialists in cardiology, neurology, pediatrics, gynecology, endocrinology, performance and movement, and more. Our exceptional clinicians also work closely with the 60+ members of the Atria Academy of Science & Medicine, top experts in their respective fields who are available for rapid consults, support, and referrals. Role Overview Atria Health is seeking a highly experienced and visionary Principal Designer. As a senior-level individual contributor in the design team, you will work with the Clinical Experience, Member Experience, and Care Delivery teams to design experiences across mobile, web, and in-practice interactions, ensuring every touchpoint with Atria is seamless, intuitive, and deeply human. This role is both strategic and hands-on—you will shape our design direction, set the standard for craft and quality, and drive the evolution of our design systems. You will partner closely with product, engineering, design, operations, and clinical teams to translate complex healthcare data and personalized care into experiences that are both emotionally engaging and operationally effective. The ideal candidate is a design leader with a track record of creating category-defining work, ideally in health tech or consumer wellness, and thrives at the intersection of vision-setting and execution. Key Responsibilities Design Strategy & Leadership - Define, champion, and evolve a multi-year design vision and strategy for the Atria experience, in alignment with company goals and product roadmap. - Serve as the principal design voice in strategic conversations, influencing at all levels of the organization. - Advocate for a member-first approach, ensuring high craft, empathy, and precise attention to detail in all design decisions. End-to-End Experience Ownership - Lead design for high-impact initiatives, from concept to launch, across multiple platforms and touchpoints. - Design quality significantly exceeds that typically found in healthcare and matches the high-touch, luxury physical experience provided at the Atria Institute. - Evolve Atria's design system into a world-class language, ensuring scalability and brand consistency across all member-facing products - Integrate service design thinking to connect digital and physical member experiences. Research, Insights & Innovation - Drive the use of qualitative and quantitative insights to inform design decisions. - Identify emerging trends and technologies in design, health tech, and consumer experiences, applying them to push Atria’s work forward. - Conduct UX research to validate and iterate on concepts, ensuring measurable impact on member satisfaction and engagement. Team & Influence - Partner closely with peers in product, design, data, and engineering to align design direction with broader strategic goals. - Influence and drive alignment across multidisciplinary stakeholders Performance & Continuous Improvement - Establish and track design KPIs tied to member engagement, retention, and satisfaction in collaboration with product partners - Continuously refine the design process to improve speed, quality, and collaboration.