Senior Data Scientist

Inspiren•New York, NY

8h•Remote

About The Position

We're looking for a Senior Data Scientist to bring rigor, modeling depth, and a bias toward automation to the data that powers Inspiren. You'll work across the organization, including with our Computer Vision, Machine Learning Engineering, Hardware, and Embedded Systems teams, building models, designing statistical evaluations, and turning one-off analyses into durable workflows that keep improving the product. You should be deeply familiar with the end-to-end ML lifecycle, comfortable reasoning about both classical statistics and modern ML systems, and energized by the opportunity to weave AI into data science workflows.

Requirements

5+ years of experience in data science, with a focus on statistical modeling and ML systems
Strong modeling and statistical foundations. You're comfortable choosing the right tool for the problem, whether simple heuristics through ML
Experience partnering with ML engineering teams, including familiarity with how production ML systems are evaluated and monitored
Fluency with a modern data science stack: Python, Pandas, PyTorch, Databricks, MLflow, or similar tools for working with data and ML at scale
Hands-on experience using AI tools (LLMs, coding copilots, agentic workflows) to speed up your own work, and curiosity to experiment with AI tools
Strong data instincts and a pragmatic bias toward solutions that work in messy, real-world conditions
A collaborative mindset and interest in working with a diverse teams
Able to scope, prioritize, and deliver work independently
Excited about working at an early-stage startup where your work directly shapes care outcomes

Nice To Haves

Experience working on spatiotemporal problems (sensor data, trajectories, event streams, or similar)
Experience working with health or clinical data
Healthcare or senior living domain experience

Responsibilities

Build models and statistical analyses that surface insights about outcomes and performance across Inspiren’s systems
Design and run rigorous evaluations: offline and online experiments (A/B, shadow deploys, etc.) for new models and product changes
Identify, evaluate, and integrate new datasets that expand what we can learn and measure
Lead root-cause investigations when models or systems underperform in the field, and turn findings into concrete recommendations for improvement
Incorporate AI into data science workflows, using LLMs and agentic tooling to accelerate analysis, code generation, documentation, and decision-making, and help shape how the team adopts these practices
Reason how to incorporate multiple modalities and sensor data into algorithmic development and performance measurement