Agent Post-Training, API & Power Users (AI)

TL;DR

Agent Post-Training, API & Power Users (AI): Training and refining frontier agentic models for API developers and power users with an accent on tool use, coding, and long-horizon execution. Focus on designing evals from real-world workflows, implementing RLHF/post-training interventions, and improving model reliability in complex agentic systems.

Location: San Francisco; Must be US-based

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 model behavior in API and power-user workflows, including function calling, tool use, and planning.
• Build evals, graders, and environments from real developer workflows to convert observed failures into training data.
• Partner with API and product teams to identify behavior gaps and implement post-training interventions.
• Develop feedback loops using power-user traces and API usage patterns to discover new model failures.
• Own end-to-end model behavior projects from qualitative failure analysis to launch readiness.
• Improve large-scale training machinery, focusing on experiment velocity, reliability, and production readiness.

Requirements

• Strong technical fundamentals in ML, software engineering, systems, or statistics.
• Hands-on experience with LLMs, post-training, RL/RLHF/RLAIF, evals, or synthetic data.
• Proven ability to analyze model traces and form concrete hypotheses for behavioral improvement.
• Experience building coding agents or tool-using agents in production ML systems.
• Must be based in the United States.

Nice to have

• Experience with multi-agent systems.
• Experience training models directly against production-like environments.

Culture & Benefits

• High-agency role with direct impact on frontier models used by millions.
• Collaborative environment working across research, engineering, and safety boundaries.
• Opportunity to push the boundaries of general-purpose AI capabilities.
• Commitment to equal opportunity and diversity in the workplace.