Staff ML Engineer (AI)

TL;DR

Staff ML Engineer (RL/Agents): Building RL environments and fine-tuning pipelines for frontier AI agents with an accent on agent-first engineering, reward design, and scalable evaluation systems. Focus on designing trustworthy verifiers, optimizing compute-economics, and developing high-throughput training infrastructure.

Location: Hybrid (3 days per week in office), San Francisco Bay Area. Must be based in the USA.

Salary: $250,000 - $280,000 USD per year

Company

hirify.global provides critical infrastructure and data-centric tools that power breakthrough AI models for leading research labs and enterprises.

What you will do

• Develop RL environments for agentic tasks, including task definitions, reward design, and high-parallelism harnesses.
• Create programmatic verifiers, LLM judges, and rubric pipelines to make agent success judgments trustworthy at scale.
• Build SFT and RL fine-tuning pipelines to convert evaluation signals into measurable model improvements.
• Design evaluation systems capable of running millions of agent trajectories to measure product quality.
• Scale training and serving infrastructure using multi-launcher orchestration and long-running job fault tolerance.

Requirements

• 3+ years of experience shipping production-grade systems.
• Proven track record in RL post-training, including SFT and at least one RL method (GRPO, PPO, DPO, or similar) in production.
• Experience building environments for AI agents and designing verifiers for open-ended tasks.
• Deep proficiency in Python and strong system/API design judgment.
• Must be based in or able to work from the San Francisco Bay Area (Hybrid).

Nice to have

• Experience with agent harnesses and coding agents as subjects of training and evaluation.
• Knowledge of multi-tenancy, sandboxing, and egress control for untrusted agent execution.
• Background in production distributed systems or large-scale ML infrastructure.
• Experience working directly with frontier AI labs.

Culture & Benefits

• High-impact, early-stage startup environment focusing on impact over process.
• Hybrid work model (3 days/week in office) in a dedicated San Francisco tech hub.
• Career advancement opportunities tied directly to individual contributions.
• Opportunity to work at the cutting edge of AI development with industry leaders.
• High-agency culture rewarding ownership and rapid execution.