Agent Post-Training, Connectors Research (AI)

TL;DR

Agent Post-Training, Connectors Research (AI): Training frontier models to interface with professional software using code, APIs, and structured integrations with an accent on post-training stacks and tool-use capabilities. Focus on designing RL experiments, building scalable eval environments, and optimizing model behavior for complex multi-step workflows.

Location: San Francisco

Salary: $295,000 – $445,000

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 complex software and plugins.
• Own end-to-end improvements to the post-training stack, including RL, data pipelines, and reward signals.
• Build evaluation environments to identify model failures and convert them into training data or research directions.
• Partner with Codex and ChatGPT product teams to translate user signal into model improvements.
• Implement early-training and alignment interventions using synthetic data and eval loops.
• Debug complex model failures and develop concrete hypotheses and fixes for shipped models.

Requirements

• Strong technical fundamentals in ML, software engineering, systems, or statistics.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, and post-training.
• Proven experience with evals, graders, synthetic data, or production ML systems.
• Ability to move from vague behavioral problems to concrete experimental pipelines.
• Comfort working across research, product, infrastructure, and safety boundaries.

Culture & Benefits

• Opportunity to work on frontier models that land directly in global products.
• High-agency environment focusing on open-ended research and engineering challenges.
• Collaborative culture spanning research, infrastructure, and safety partners.
• Equal opportunity employer with a commitment to diverse perspectives.