Research Engineer - Post training & RL
Core
Design dynamic simulations and post-training algorithms to evaluate and advance frontier LLM reasoning and long-horizon behavior.
Role type
Research Engineer (Post-training & RL)
Builds
Reinforcement learning environments, reward models, and evaluation frameworks for next-generation AI.
Domain
Artificial Intelligence / Machine Learning / Reinforcement Learning
Deliverable
production ML models
Required skills
Post-training algorithms, reinforcement learning, transformer models, experimental design, LLM evaluation
Preferred skills
None stated
Technologies
None explicitly listed
Responsibilities
Create dynamic simulations that measure real intelligence; design new post-training algorithms (RLHF, DPO, GRPO); develop richer reward models; build evaluation frameworks.
Seniority
Senior, hands-on IC
Sourced via techire · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.