Applied Reinforcement Learning Engineer

Centific Global

Palo Alto, CA, US
Base: $150k - $300k annually; bonus/equity: not sp...
Hybrid
Deep reinforcement learning expertise
Llm post-training with rlhf dpo ppo
Custom environment design gymnasium
Centific is a frontier AI data foundry empowering enterprises with safe, scalable AI deployment through purpose-built technology platforms

Job Summary

  • Centific is a frontier AI data foundry empowering enterprises with safe, scalable AI deployment through purpose-built technology platforms.
  • The role involves designing custom RL environments that simulate complex enterprise workflows to train intelligent agents within them.
  • Candidates will translate cutting-edge RL research into production systems while contributing to publications and shaping product direction.

Matching Summary

Centific is a frontier AI data foundry empowering enterprises with safe, scalable AI deployment through purpose-built technology platforms.

Salary

Base: $150K - $300K Annually; Bonus/Equity: Not specified; Benefits: Not specified

Skills & Requirements

Must-have

  • Deep Reinforcement Learning expertise
  • LLM post-training with RLHF DPO PPO
  • Custom environment design Gymnasium
  • Python programming skills
  • Agentic AI tool use experience

Nice-to-have

  • Publications at NeurIPS ICML ICLR
  • Experience in healthcare or finance domains
  • Open-source contributions to agent frameworks
  • World models and synthetic data generation
  • Distributed training large-scale experimentation

Key Requirements

  • 3+ years hands-on Deep RL experience
  • MS/PhD in CS ML or equivalent experience
  • Strong software engineering beyond research

Work Rights

Not specified

Tailored Resume

Cover Letter