Researcher, Connectors - Agent Post-Training (AI)

TL;DR

Researcher, Connectors - Agent Post-Training (AI): Training frontier agents to interface with professional software using code and APIs with an accent on post-training techniques like RL and RLHF. Focus on building training signals, evals, and feedback loops to enable complex multi-step workflows across digital contexts.

Location: San Francisco

Salary: $250,000 – $380,000 USD + 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 execute experiments to improve agentic model behavior for complex software and plugins.
• Develop end-to-end improvements in the post-training stack, including RL, data pipelines, reward signals, and model-behavior analysis.
• Create evals and environments to identify model failures and convert them into training data, product fixes, or research directions.
• Collaborate with Codex and ChatGPT product teams to translate user needs into model improvements.
• Implement early-training and alignment interventions, including data mixtures, objectives, and synthetic data.
• Optimize large-scale training machinery for better velocity, reliability, and production readiness.

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 translate vague behavioral problems into concrete experiments, hypotheses, and fixes.
• Comfort working across research, product, infrastructure, and safety boundaries.
• Experience with coding agents, tool-using agents, or synthetic data generation.
• Must be located in San Francisco

Culture & Benefits

• Opportunity to work on frontier models that land directly in products used by millions of people.
• High-agency environment focusing on open-ended research and engineering challenges.
• Competitive compensation including significant equity offers.
• Collaborative culture across multidisciplinary teams including safety, alignment, and infrastructure.