Researcher, Computer Use - Agent Post-Training (AI)

TL;DR

Researcher, Computer Use - Agent Post-Training (AI): Developing and training frontier agents capable of operating computers, browsers, and desktops with an accent on RL, RLHF, and post-training signals. Focus on building robust environments, graders, and data pipelines to improve agent reliability and long-horizon execution.

Location: San Francisco, USA

Salary: $250,000 – $380,000 + Equity

Company

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

What you will do

• Design and run experiments to improve agentic model behavior for desktop and browser computer use.
• Own end-to-end post-training improvements including RL, data pipelines, reward signals, and evaluations.
• Build evaluation environments to identify model failures and convert them into training data or research directions.
• Collaborate with Codex and ChatGPT product teams to translate user needs into model improvements.
• Work on early-training interventions, including data mixtures, synthetic data, and alignment loops.
• Debug complex failures in shipped models and develop concrete hypotheses for technical fixes.

Requirements

• Strong technical fundamentals in machine learning, software engineering, systems, or statistics.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, or production ML systems.
• Ability to move from vague behavioral problems to concrete, executable experiments.
• Comfort working across research, product, infrastructure, and safety boundaries.
• Experience with coding agents, tool-using agents, or synthetic data generation.

Culture & Benefits

• Opportunity to work on frontier models that land directly in global products.
• High-agency environment solving open-ended, complex AI problems.
• Competitive compensation package including equity.
• Inclusive work culture as an equal opportunity employer.