Staff Data Scientist

Who We Are :   At Synapse Health,  we're  streamlining the durable medical equipment (DME) process.  We manage intake, documentation, routing, claims, billing, and patient support. Our model reshapes how DME is delivered and experienced.    Since  2016,  with decades of industry and leadership experience,  we've  delivered tech-based solutions that help our partners to modernize operations, improve coordination, and reduce administrative burdens. By taking on operational and financial complexity,  we're  redefining how DME works for providers, prescribers, and patients. We are proud to offer  work that matters, on a mission that matter s .     Learn more at   SynapseHealth.com   and on   Synapse Health’s LinkedIn .     What We Need :     The Staff Data Scientist reports directly to the Director of Data Science and Analytics. Our operations team processes tens of thousands of DME orders every day, and  we've  now processed millions of orders overall — giving us the data to build real prediction engines rather than just react  order  by order. This role is a senior, highly independent IC: you  don't  manage people, but  you're  expected to own hard problems end to end, mentor senior data scientists on the team, and bring the technical judgment of someone who could.   The problems we need to solve include:   Vendor matching  — deciding which vendor fulfills each incoming order,  optimizing for  patient experience, delivery speed, and cost. Requires strong predictive ML (classification, regression) and optimization skills.   Order routing  —  identifying  the most efficient path from order creation to delivery and flagging orders at risk of delay. Requires predictive ML and, ideally, reinforcement learning for sequencing decisions over time.   Supply chain optimization  — finding root-cause bottlenecks across in-flow and out-flow and quantifying the counterfactual impact of fixing them. Requires operations research methods (queueing theory, network flow optimization, discrete event simulation) and causal inference.   Agentic AI  — evolving these systems from ones that recommend actions to ones that take them directly, once proven trustworthy. Requires experience building agentic AI tools and designing confidence thresholds and decision logic for autonomous action.   This mandate  isn't  fixed — as Synapse's data science footprint grows into Revenue Cycle Management, Finance initiatives like anomaly detection, and beyond, this role is expected to flex and take on new problem areas alongside the rest of the team.     What You Will Do :     Build and own models across vendor matching, order routing, and supply chain optimization, expanding into new problem areas as priorities shift    Architect confidence thresholds and decision logic that let systems act autonomously once proven trustworthy, pushing the team's work toward agentic AI    Quantify the counterfactual for your work: prove out impact with real numbers, not assumptions    Ship models end to end, from experimentation through production, in close partnership with data engineering    Apply the right technical approach to the problem — predictive ML, causal ML, reinforcement learning, operations research, or causal inference — rather than defaulting to one toolkit    Mentor senior data scientists on the team, raising the technical bar without formal management responsibility    Write clear technical design docs and hold your own work to a high bar    Partner with the Director and the rest of the team to break work into quarterly, leverage-sequenced priorities    Stay flexible as the team's scope expands into Revenue Cycle Management, Finance, and other domains   Note: These responsibilities reflect the general nature and scope of the role but are not exhaustive. Responsibilities may evolve to meet changing business needs.   What You Have :      At Synapse Health,  we’ve  intentionally built a culture rooted in kindness, collaboration, and creativity, qualities we consider essential for every team member.  Additional  requirements include:   Education —  Master's  degree  required  in a quantitative field (Computer Science, Statistics, Data Science, Operations Research, or related)    Experience — 7+ years in data science, with  a track record  as a highly independent, senior IC   Prior experience at an early-stage healthcare startup, with hands-on  expertise  in claims data and other healthcare data.   Strong technical foundation in standard predictive ML (classification, regression, forecasting)    Strong hands-on  proficiency  in Python and SQL — able to write, debug, and optimize production-quality code, not just prototype in a notebook   Understands the full software development lifecycle and works fluently with GitHub — version control, branching strategies, pull requests, and code review — as a standard part of shipping models into production.   Track record  shipping ML products end to end, from experimentation through production, in close partnership with data engineering    Able to write technical design docs and hold your own work to a high standard    Demonstrate effective verbal and written communication skills, including presenting findings to technical and non-technical stakeholders    Demonstrate strong analytical and organizational skills, managing multiple workstreams and priorities    Comfortable operating in a high-pressure, ambiguous environment where priorities shift and requirements  aren't  always fully defined   What Sets You Apart :     Candidates are expected to have hands-on experience in  several  — not necessarily all — of these areas, along with the ability to quickly learn new ones:   Offline and online reinforcement learning for sequencing decisions that improve in-flow/out-flow over time   Operations research methods (queueing theory / Little's Law, network flow optimization, discrete event