Applied Scientist (Optimization & Logistics)
Posted Updated
Description
- We’re looking for an Applied Scientist to turn Sprinter’s hardest logistics problems into optimization models and decision systems that get the right clinician to the right patient at the right time
- Sprinter runs a two-sided operation — clinicians on one side, patients who need care at home on the other — and we must match supply to demand across large regions under complex constraints
- As an Applied Scientist, you will take ambiguous operational problems and shape them into well-posed tasks, strong baselines, and honest evaluations
- The algorithms you build will answer questions like which clinician sees which patient, in what order, given drive time, appointment windows, and clinical constraints; how many clinicians to staff in each region next month; and how long a visit will take or whether a patient is likely to cancel
- This role sits at the intersection of research and engineering, blending scientific rigor with a deployment-oriented mindset
- It also requires close cross-functional partnership with operations, product, and engineering stakeholders
- Turn ambiguous operational problems into well-posed optimization, forecasting, or simulation tasks
- Build strong baselines and improve on them efficiently, adding complexity only when the value justifies it
- Develop solutions across operations research, optimization, and machine learning, choosing the right tool for the problem
- Run careful analysis and iterate toward decisions that improve real operational outcomes — cost per visit, clinician utilization, patient access, and visits completed
- Design offline evaluations, simulated backtests, and live experiments that predict real-world operational impact
- Find the gaps between a model’s assumptions and messy operational reality before they reach production
- Choose metrics suited to stochastic, constrained, and partially observed operational systems
- Interpret and communicate results effectively to cross-functional stakeholders
- Partner with Engineering to productionize optimization and decision systems reliably
- Work with operations partners and SMEs to validate assumptions and review where decisions break down
- Explain tradeoffs, uncertainty, and limitations clearly to product and leadership
Benefits
- Free lunch everyday and fully-stocked microkitchens and coffee/tea bar
- Team offsites, game hours, tech talks, and design sprints
- Health insurance benefits (PPO / HMO / HSA, 100% of family premiums paid)
- Dental / vision / wellness benefits
- 401k matching
- Unlimited PTO
- Flexible work-from-home policy for work/life balance (4 days in-office, accommodation for occasional WFH days)
- Relocation assistance
- Generous parental leave (4 months for the birthing parent, 3 months for a partner, 100% paid)
- The ideal candidate is a scientist-engineer who reasons from first principles about uncertainty and constraints, reaches for the simplest model that works, and can move from a formulation on the whiteboard to a decision that runs in production
- Strong foundations in operations research or optimization: modeling, algorithms, experimental design, and honest evaluation
- Ability to turn an ambiguous problem into a well-posed optimization or forecasting task, discover and analyze related literature, and adapt/apply those methods to our tasks
- Fluency with AI coding assistants (e.g., Claude Code, Cursor) in your day-to-day development workflow
- Interest in operations collaboration and applied healthcare impact
- Judgment about how uncertainty, constraints, and edge cases behave in real-world operational data
- Strong Python and SQL, the standard optimization and ML libraries, and the ability to run your own experiments end to end
- MS or PhD in operations research, industrial engineering, computer science, applied math, statistics, machine learning, or a related quantitative field; exceptional applied experience can substitute
- Depth in a relevant area such as vehicle routing, scheduling, stochastic optimization, discrete-event simulation, queueing, or demand forecasting
- Experience shipping optimization or decision systems that reached production and had material real-world impact
- Hands-on experience with supply-and-demand matching in a marketplace, dispatch, or field-operations setting
- Fluency deciding when an exact optimization approach beats a heuristic or learned one, and vice versa
- We aim to complete the interview process between 2–3 weeks. It will usually consist of:
- Recruiter Screen (30 minutes)
- Hiring Manager Introduction (30 minutes)
- Hands-on-Keys Technical Assessment (1 hour)
- Onsite Interview: Systems Design / Technical Case Study + Research Presentation + Behavioral Interview + Lunch with the Team (4 hours)
- References
Skills
Sign in to read and join the discussion.