Senior Software Engineer-ML Platform

Roblox•San Mateo, CA
•$196,750 - $243,290•Onsite

About The Position

As a Senior Software Engineer on the User Behavior ML Platform, you will build the data and serving foundation for Roblox's user-level safety understanding. You will own the core ML platform for a safety user feature store, user embeddings, and risk scores that support personalized consequences, proactive detection, and early education. The systems will help safety teams understand risk across hundreds of millions of users and will directly affect users, including minors. The role includes designing and operating feature pipelines, bringing embeddings and risk models from offline training into production, and extending batch processing to real-time streaming. You will partner with ML engineers and data scientists to provide self-serve tooling and build monitoring and governance for data quality. You will deliver systems end to end, from design through migration, testing, production operation, and on-call, with an emphasis on explainability, fairness, auditability, and appeals correction.

Requirements

  • At least 5 years of experience building and operating production ML platforms, data infrastructure, or large-scale backend systems.
  • Strong experience with batch and streaming data pipelines, such as Spark, Flink, or Kafka, feeding feature stores or similar ingestion layers.
  • Experience designing low-latency serving systems, including service APIs (RPC/gRPC), key-value storage, caching, and high-throughput read paths.
  • Proficiency in Python and a statically typed backend language such as Go or Java.
  • Production operations fundamentals, including monitoring, alerting, on-call, and incident response for systems with real user-facing impact.
  • Comfort partnering with ML engineers and a working understanding of the model lifecycle, including training data generation, offline evaluation, deployment, and drift monitoring.

Nice To Haves

  • Experience in Trust & Safety, content moderation, user detection, or other adversarial domains.
  • Experience with user-level modeling or user understanding.
  • Experience with embeddings and vector similarity search in production.
  • Familiarity with feature store platforms and signal governance.
  • Experience building agentic workflows or tool interfaces for LLM agents, such as MCP.

Responsibilities

  • Design and operate pipelines that turn violations, reports, appeals, filter activity, and engagement signals into reliable, documented user features for training and serving.
  • Take user embeddings and risk models from offline training to production, including low-latency online lookup and similar-user search for detection teams.
  • Extend batch pipelines to streaming so fresh behavioral signals reach models and downstream safety systems within minutes.
  • Partner with ML engineers and data scientists to provide self-serve tooling for feature discovery, training data generation, offline evaluation, and A/B experiment hooks.
  • Build monitoring for feature freshness, drift, lineage, and ownership to support trusted reuse of signals across Safety teams.
  • Build systems that support explainability, fairness review, and appeals correction.
  • Own end-to-end delivery, including system design, migration, testing, production operation, and on-call.

Benefits

  • Equity compensation for full-time employees.
  • Benefits are offered, but the specific benefits are not listed in the posting.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service