Why Work For Us
Grubhub, part of Wonder Group Inc, is all about connecting hungry diners with our network of over 375,000 merchants nationwide. Innovative technology, user-friendly platforms and streamlined delivery capabilities set us apart and make us an industry leader in the world of online food ordering. When you join our team, you become part of a community that works together to innovate, solve problems, grow, work hard and have a ton of fun in the process!
About the Role
At Grubhub Fulfillment Decision Modeling, our mission is to build decision-making systems that power a world-class logistics network. As a Staff Decision Scientist, you will go beyond individual problem solving—you will shape the strategic direction of decision modeling frameworks across Fulfillment, mentor senior and junior scientists, and collaborate closely with engineering to move our decision intelligence capabilities toward scalable, production-grade systems.
You will identify the highest-leverage decision points in our marketplace (ETA setting, dispatching, routing, pricing, and transmission timing), design mathematically principled frameworks to optimize them under uncertainty, and lead the technical evolution toward sequential, adaptive decision systems. You will help define how we structure trade-offs like speed vs. cost, variance vs. confidence, and reliability vs. optimization aggressiveness. You’ll prototype, experiment, influence architecture, and ensure we operationalize models that actually move business metrics—not just models that look good offline.
The Impact You Will Make
- Serve as a technical thought leader in Decision Modeling within Fulfillment — defining principles, frameworks, and best practices for how Grubhub makes dispatch, ETA, routing, and pricing decisions at scale.
- Mentor and coach a growing team of Decision Scientists and contribute to career development and technical excellence across the group.
- Lead the exploration of interdependent decision layers, recognizing feedback loops between ETA policy, transmission timing, routing, and dispatch logic.
- Partner with engineering to drive architecture decisions for shared data layers, modeling APIs, and real-time decision services.
- Define and implement robust experimentation strategies for decisions that move business metrics by seconds or cents in high-noise environments.
- Champion a shift from pure predictive modeling to true decision intelligence, integrating optimization, heuristic search, and risk-aware inference into systems that learn and adapt.
What You Bring to the Table
- 8+ years of industry experience with MS or 6+ years with PhD in Operations Research, Applied Mathematics, Computer Science, Optimization, or related quantitative fields.
- Proven experience framing business processes as structured decision problems (e.g., resource allocation, vehicle routing, assignment, ETA forecasting with decision impact awareness, supply/demand balancing under noise).
- Deep expertise with formulating and solving optimization problems (MIPs, heuristics, stochastic optimization, routing algorithms). Experience with Gurobi, CPLEX, or Xpress.
- Strong intuition for decision impact trade-offs — speed vs. cost, ETA confidence vs. conversion risk, dispatch aggressiveness vs. courier incentives, etc.
- Proficiency in Python, data analysis, visualization, and writing scalable, production-ready code using object-oriented design.
- Demonstrated ability to take decision models into production , partnering with engineering on architecture and deployment best practices.
- Fluency in SQL or similar tools for directly interrogating production-scale datasets.
- Experience mentoring and providing technical direction to other scientists or engineers.
Got any of these? Even better
- Experience leading end-to-end design of decision-making or planning frameworks within real-time logistics or marketplace systems.
- Experience designing sequential decision systems with ML and optimization feedback loops rather than isolated point predictions.
- Background in stochastic control, Bayesian decision theory, or variance-aware modeling for dynamic systems.
- Experience with real-time event-driven production systems and applied experimentation frameworks (A/B testing, power analysis under noisy conditions).
- Influence across disciplines — able to align product, engineering and science around a cohesive decision architecture vision.
- Experience defining strategy and technical roadmaps for decision modeling platforms.
Base Salary:
New York: $240,000- $249,500
Illinois: $216,000- $224,500