Research Engineer, Post-Training (AI)

Location: New York City; cozy office in NYC.

Company

hirify.global builds Per-Account Agents that research accounts, identify opportunities, and advance sales next steps across the revenue lifecycle.

What you will do

• Develop post-training recipes across datasets, training stages, and hyperparameters.
• Design evaluation systems that reflect production performance and maintain evaluation integrity.
• Investigate unexpected training results, identify causes, and transfer findings to future experiments.
• Apply and advance RLHF, RLAIF, and constitutional approaches to shape agent reasoning, actions, and human collaboration.
• Measure performance scaling with data and compute and develop new methods when existing approaches reach their limits.
• Work directly with the founders on intelligence quality for GTM and sales applications.

Requirements

• At least 3 years of full-time experience.
• Track record of advancing ML systems through post-training, alignment, or related methods such as RLHF, RLAIF, preference modeling, or reward learning.
• Strong fundamentals in probability, statistics, and machine learning theory.
• Ability to distinguish real effects from noise and bugs in experimental data.
• Evidence of original contributions or comparable industry work, preferably in startup environments.
• Ability to understand end-user tasks and develop intuition for judging what good, great, and bad performance looks like.

Culture & Benefits

• High-ownership environment focused on outcomes, first principles, urgency, and direct customer impact.
• Competitive early-stage equity.
• Health, dental, and vision coverage.
• Unlimited PTO, recharge days, annual off-sites, and monthly events.
• Catered lunch on Tuesdays and Fridays, daily dinners, and a fully stocked kitchen.
• Cutting-edge technology and tools, commuter benefits, and a cozy NYC office.