Principal Product Manager, Rides Matching

About the role

Bolt is a global mobility platform used by more than 200 million customers and 4.5 million driver and courier partners across 50 countries. Every ride order flows through its matching system, which is being evolved from a heuristic-based dispatch system toward a context-aware, probability-based allocation engine powered by machine learning and reinforcement learning. As Principal Product Manager, you will own this transition end to end, define the roadmap, build a cross-functional pod of engineers, data scientists and specialists, and be accountable for both the performance of the existing system and the delivery of the next generation.

Key responsibilities

• Define the product strategy and roadmap for the dispatching engine, sequencing foundational ML/RL investments alongside near-term improvements to queue ranking, dispatch strategy and retry governance.
• Coordinate the productionisation of ML and RL models, from offline training through shadow mode, A/B testing, incremental rollout and live monitoring across markets.
• Own and improve the performance of the existing matching stack while the new engine is built, maintaining stability and delivering efficiency gains.
• Define and maintain the signal contract between matching and pricing, ensuring reliable, low-latency completion probability and supply density signals.
• Design experiments, evaluate results and turn complex algorithmic trade-offs into clear recommendations for senior stakeholders.
• Set priorities and resolve trade-offs within a cross-functional pod, acting as the accountable owner for matching KPIs.

Required profile

• Experience shipping ML models into production systems serving real-time allocations at scale, owning the full lifecycle from feature engineering and training through shadow deployment, monitoring and iteration.
• Work on allocation, matching, dispatch or equivalent real-time systems in a two-sided marketplace, logistics platform or high-throughput environment, with a strong grasp of supply-demand dynamics and global versus local optimisation trade-offs.
• Track record of keeping a live production system stable while building its replacement during a migration.
• Experience coordinating cross-functional product pods and negotiating interface contracts with teams such as pricing or economics.
• Ability to move between detailed statistical evaluation and clear stakeholder communication, producing strategy documents, technical specifications and experiment reviews.
• Direct exposure to reinforcement learning in production, or work with teams that deployed RL systems, with a solid grasp of reward design, exploration-exploitation trade-offs and the gap between simulation and live environments.

What we offer

• A competitive salary and stock options.
• Wellness perks and a 1-month paid sabbatical after 5 years.
• Hybrid model with at least 12 monthly in-office days.
• Annual company events and smaller team gatherings.