Skip to main content
All jobs

Employer listing

Principal Machine Learning Engineer - Matchmaking

Roblox

San Mateo, Ca · hybrid · full time · Principal

$295,250 - $345,040

About the Role

Matchmaking is a critical stage downstream of Discovery and Search. Once a player chooses a game to play, matchmaking assigns them to a server for that game. That decision shapes who they play with, the network latency they experience, and the quality of their session. By matching players to servers that fit their needs and each developer’s game, matchmaking helps turn discovery into satisfying play, repeat visits, and long-term engagement, making it a direct lever for Roblox’s growth.

As a Principal ML Engineer on Matchmaking, you’ll own the technical vision and execution for the models, objective functions, and algorithms that make those decisions. You’ll combine predictions of high-value player actions with optimization of player and developer utility and system efficiency, serving millions of players across hundreds of thousands of servers in global datacenters.

Responsibilities

  • Own the technical direction and ML strategy for matchmaking, connecting the Discovery and Search journey to server placements that improve player experience, developer success, and Roblox growth.
  • Define and evolve the matchmaking objective function to balance player and developer utility with system efficiency. Make tradeoffs among co-player compatibility, network and join latency, engagement, retention, server utilization, and compute cost explicit and measurable.
  • Build models that predict high-value actions and longer-term outcomes for each player–server match, including co-play, chat engagement, sustained play, and return visits, using player history, game characteristics, and live server state.
  • Design and productionize candidate-server retrieval, ranking, and assignment algorithms that optimize this objective under real-time latency, capacity, and reliability constraints, accounting for both the joining player and players already in the server.
  • Lead other engineers by example and through technical direction as an individual contributor, mentor engineers, and create an engineering culture of excellence.
  • Build and evolve the data, feature, training, serving, and evaluation systems that support matchmaking ML, ensuring fresh signals, reliable predictions, and consistency between training and serving.
  • Partner with Discovery, Search, developer-facing product teams, modelers, and data and AI infrastructure engineers to co-design models and systems that adapt to each game’s needs and deliver value across the player journey.
  • Define offline evaluation and lead online experiments to measure the impact of matchmaking decisions on player engagement and retention, developer success, and system efficiency, using the results to improve models and objectives.
  • Translate research into iterative production improvements, collaborate with the wider ML community where applicable, and represent Roblox’s technical work.

Qualifications

  • 8+ years of experience and a consistent record of delivering and improving large-scale ML systems for ranking, recommendation, personalization, or resource allocation.
  • Experience defining objective functions, building predictive models, and deploying optimization algorithms that balance user and business outcomes with production latency, reliability, and resource constraints.
  • The capability of breaking down long-term product requirements into iterative deliverable stages.
  • Initiated and facilitated challenging technical decisions across multiple teams and organizations with empathy.
  • Deep technical expertise, starting with the needs of the user (players and internal engineers).
  • A generalist approach with mastery of multiple languages and technologies and the ability to adapt to any situation.
  • Ability to roll up your sleeves to tackle data or machine learning problems as they arise.
  • Creative and strategic approach to simplifying complex problems.
  • BS in Computer Science or a related discipline; MS or PhD is a plus.

Work Arrangement

Roles based in an office are onsite Tuesday, Wednesday, and Thursday, with optional presence on Monday and Friday.

Benefits

All full-time employees are eligible for equity compensation and company benefits.