Staff ML Engineer, Agent Training & Environments
Hybrid (San Francisco Bay Area)$250k - $280kFull-timePosted 2mo ago
About the role
Labelbox is seeking a Staff ML Engineer focused on agent training environments and post-training RL workflows. The role combines building scalable RL environments, verifiers, and fine-tuning pipelines with engineering throughput and platform reliability to advance frontier agent capabilities.
Responsibilities
- RL environments for agentic tasks: task definitions, tool surfaces, state and reset semantics, reward design — and the harness that runs thousands of them in parallel
- Verifiers and graders: programmatic checks, LLM judges, rubric pipelines, pass@k scoring. Deciding what "the agent succeeded" means, and making that judgment trustworthy at scale
- Fine-tuning pipelines that turn evaluation signals into measurable agent improvements — SFT and RL, from data collection through training to checkpoint evaluation
- Eval systems that run millions of agent trajectories to measure model and product quality
- Training and serving infrastructure that scales to the throughput frontier labs need: multi-launcher orchestration, long-running job fault tolerance, cost accounting
Qualifications
- 3+ year track record of shipping systems that customers and other engineers rely on
- Strong system and API design judgment
- Production code experience with coding agents daily
- Proven ability to build the substrate for others' work: tooling, CI, harnesses, libraries
- Ability to operate in fast, ambiguous startup environments
- Deep proficiency in Python, comfortable across the stack
- Experience in RL post-training with fine-tuned models for agentic tasks and SFT plus RL methods in production
- Experience designing verifiers/graders for open-ended tasks
- Ability to reason about compute-economics and optimize experiments
Skills
Required:PythonSystem designRLHF / RL methods (e.g., SFT, PPO, GRPO, DPO)
Benefits
- Competitive compensation reflecting experience
- Stock options
- Health, dental, and vision insurance
- Flexible PTO and supportive work culture
- Opportunity to impact frontier AI tooling at scale
Last updated Sep 2, 2026. Interested? Apply on the company site.
About Labelbox
The data factory for AI teams
Labelbox delivers the software and services to help you build, operate, or staff your data factory
AI teamsdata factorylabeling servicesplatform & toolsfrontier AIresearchmachine learningmodel evaluation
More open roles at Labelbox
- Member of Technical Staff4w agoHybrid (San Francisco Bay Area) · Alignerr Services
- Global Specialized Domain Expert Recruiter (Contractor)2mo agoRemote · Marketing
- Forward Deployed Engineering Manager4mo agoHybrid (San Francisco Bay Area) · Alignerr Services
- Managing Partner4mo agoHybrid (San Francisco Bay Area) · Alignerr Services
- Forward Deployed Research Scientist6mo agoHybrid (San Francisco Bay Area) · Alignerr Services