Researcher, Agent Post-Training (AI)

TL;DR

Researcher, Agent Post-Training (AI): Training the next generation of frontier agents for Codex and ChatGPT with an accent on tool use, computer operation, and multi-agent coordination. Focus on developing training signals, RLHF pipelines, and evals to improve model reliability and product fit.

Location: San Francisco, USA

Salary: $295K – $445K

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 across coding, tool use, function calling, and multi-agent collaboration.
• Own end-to-end improvements to the post-training stack, including RL, data pipelines, graders, and reward signals.
• Build evals and environments to expose model failures and convert them into training data or research directions.
• Partner with product teams (Codex, API, ChatGPT) to translate user needs into concrete model improvements.
• Develop early-training and alignment interventions using synthetic data, objectives, and eval loops.
• Optimize large-scale training machinery for improved velocity, reliability, and production readiness.

Requirements

• Must be based in or able to work from San Francisco, USA
• Strong technical fundamentals in machine learning, software engineering, systems, or statistics.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals, or production ML systems.
• Ability to translate ambiguous behavioral problems into concrete hypotheses and experiments.
• Experience with coding agents, tool-using agents, or synthetic data generation.
• Ability to communicate effectively across research, product, and infrastructure boundaries.

Culture & Benefits

• High-agency role where research and engineering work lands directly in frontier models.
• Opportunity to shape the capabilities of AI systems used by millions of users globally.
• Collaborative environment working with world-class researchers, engineers, and safety partners.
• Inclusive culture committed to safety and ensuring AI benefits all of humanity.