# Staff ML Engineer, Agent Training & Environments **Company**: Labelbox **Location**: San Francisco **Work arrangement**: hybrid **Experience**: staff **Job type**: full-time **Salary**: $250,000-$280,000 USD **Category**: Engineering **Industry**: Technology **Apply**: https://job-boards.greenhouse.io/labelbox/jobs/5199053007?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply **Canonical**: https://yubhub.co/jobs/job_2327bed9-ab4 ## Description ## Shape the Future of AI At Labelbox, we're building critical infrastructure for breakthrough AI models at leading research labs and enterprises. Since 2018, we've pioneered data-centric approaches fundamental to AI development. ## Role Overview Labelbox is the RL data factory for advancing frontier agent capabilities. We build the data, environments, and evaluations that frontier labs use to train and judge their agents. This role sits where training meets infrastructure. You will run experiments and build systems that run them: environments agents act in, verifiers that decide whether they succeeded, and fine-tuning pipelines that turn that signal into a better model. ## Responsibilities - Develop RL environments for agentic tasks, including task definitions, tool surfaces, state and reset semantics, reward design, and the harness that runs thousands of them in parallel. - Create verifiers and graders, such as programmatic checks, LLM judges, rubric pipelines, and pass@k scoring. - Design fine-tuning pipelines that turn evaluation signals into measurable agent improvements , SFT and RL, from data collection through training to checkpoint evaluation. - Build eval systems that run millions of agent trajectories to measure model and product quality. - Develop training and serving infrastructure that scales to the throughput frontier labs need: multi-launcher orchestration, long-running job fault tolerance, cost accounting. ## Requirements As an engineer: - A 3+ year track record of shipping systems that customers and other engineers rely on. - Exceptional throughput without sacrificing quality. - Strong system and API design judgment. - Daily experience with coding agents and shipping production code. - Deep proficiency in Python and comfort across the rest of the stack. As an RL post-training practitioner: - Experience fine-tuning models for agentic tasks and making them measurably better. - Built environments agents operate in, with expertise in reward and task design. - Designed verifiers or graders for open-ended work. - Debugging training runs forensically and methodically. - Understanding of compute economics. ## Nice to Have - Experience with agent harnesses and coding agents as subjects of training and evaluation. - Knowledge of multi-tenancy and isolation for untrusted agent execution. - Background in production distributed systems, ML infrastructure, or data systems at scale. - Experience working directly with frontier labs or highly technical customers. ## Benefits - High-impact environment with expanded responsibilities and career growth tied to contributions. - Technical excellence and collaboration with industry leaders. - Innovation at speed with ownership and rapid execution. - Continuous growth and learning with curious minds. - Clear ownership and autonomy to execute. ## Compensation - Expected annual base salary range: $250,000-$280,000 USD. ## Life at Labelbox - Location: San Francisco. - Work style: Hybrid model with 3 days per week in office. - Environment: Fast-paced and high-intensity. - Growth: Career advancement opportunities directly tied to impact. ## Skills ### Required - Python - RL - ML - API design - System design ### Nice to have - Agent harnesses - Multi-tenancy - Distributed systems - ML infrastructure --- Source: [Apply at job-boards.greenhouse.io](https://job-boards.greenhouse.io/labelbox/jobs/5199053007?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)