Agent Post-Training, Frontier Evals and Environments Research (AI)

TL;DR

Agent Post-Training, Frontier Evals and Environments Research (AI): Building and optimizing frontier agents and evaluation environments to drive progress towards AGI/ASI with an accent on RL environments, model capabilities, and automated behavior exploration. Focus on designing scalable evaluation systems, creating self-improvement loops, and steering the largest training runs at hirify.global.

Location: San Francisco (Onsite)

Salary: $295K – $445K

Company

AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Create ambitious RL environments to measure frontier model capabilities, skills, and behaviors.
• Develop new methodologies for automatically exploring the behavior of frontier models.
• Analyze the science of measurement, focusing on scalability, reliability, and variance of evaluation methodology.
• Steer training for the largest training runs to guide future model capabilities.
• Design scalable systems and processes to support continuous evaluation.
• Build self-improvement loops to automate model understanding.

Requirements

• Strong technical fundamentals in machine learning, software engineering, systems, or statistics.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data, or production ML systems.
• Ability to transition from vague behavioral problems to concrete experiments and pipelines.
• Comfort working across research, product, infrastructure, data, evals, and safety boundaries.
• Capability to communicate clearly with diverse technical and non-technical groups.

Culture & Benefits

• High-agency role with work landing directly in frontier models.
• Collaboration with researchers, engineers, product teams, and safety/alignment partners.
• Opportunity to steer the most ambitious training runs in the industry.
• Commitment to equal opportunity and diverse perspectives.