Staff Machine Learning Engineer (Agent Training & Environments)

Join Labelbox, the leading RL data factory for advancing frontier agent capabilities. As a Staff Machine Learning Engineer, you will be at the intersection of training and infrastructure, running experiments and building systems that drive agent training and evaluation. You will work on RL environments, verifiers, fine-tuning pipelines, eval systems, and training infrastructure. This role offers a flexible vacation policy, 401k program, college savings account, HSA, daily lunches, virtual wellness programs, a dog-friendly office, regular social events, and professional development benefits.

• Conduire des expériences et construire des systèmes pour exécuter des expériences, y compris des environnements dans lesquels les agents agissent, des vérificateurs qui décident de leur succès et des pipelines d'affinage.
• Développer des environnements d'apprentissage par renforcement pour des tâches agentiques, y compris la définition des tâches, les surfaces d'outils, la conception des récompenses et l'exécution de milliers d'entre eux en parallèle.
• Concevoir des vérificateurs ou des évaluateurs pour des travaux ouverts, en s'assurant qu'ils sont fiables à grande échelle et en prenant des décisions éclairées sur ce que signifie "le succès de l'agent".
• We're looking for someone who does both halves — the engineering throughput of a strong platform engineer, and real depth in post-training agents
• The bar is high: engineers with strong judgment who set technical direction, turn prototypes into reliable systems fast, and are at the frontier of agent-first engineering practice
• You move fast in ambiguous, startup-pace environments, with influence over authority
• Strong system and API design judgment. Hard architecture calls land with you: you make them, defend them under pressure, and update fast when someone else is right
• You ship production code with coding agents daily. You know where they break and what it takes to make them reliable, and you use that to move the whole team faster
• A 3+ year track record of shipping systems that customers and other engineers still rely on
• Exceptional throughput, without the quality tax. You ship a lot, you review a lot, and the v1 you ship becomes the foundation the rest of the team builds on
• You build the substrate other people's work runs on — tooling, CI, harnesses, libraries — and you treat that as the job, not a distraction from it
• Deep proficiency in Python, and comfort across the rest of the stack
• You have fine-tuned models for agentic tasks and made them measurably better. SFT plus at least one RL method (GRPO, PPO, DPO, or similar) in production
• You have built environments agents operate in, and you know why reward and task design is where most of the difficulty actually lives
• You have designed verifiers or graders for open-ended work, and you know how they get gamed
• You reason about compute-economics. You know what an experiment costs, when a run is not worth finishing, and how to get the same signal for a tenth of the spend
• You write up what you learned so it changes what the team does next
• You debug training runs forensically and methodically
• Experience with agent harnesses and coding agents as subjects of training and evaluation
• Multi-tenancy and isolation for untrusted agent execution: sandboxing, egress control, credential handling
• Background in production distributed systems, ML infrastructure, or data systems at scale
• Experience working directly with frontier labs or other highly technical customers