Sr. Model Engineer, Post-Training & RL
xAIPalo Alto, CAOn-Site
Needs a free Superjobs account. You'll finish on xAI's Greenhouse page.
Skill score
Summary
This role runs post-training and reinforcement learning work on frontier models, including reward modeling, preference optimization, and experiments that turn research ideas into measurable capability gains. It suits engineers with hands-on experience training large neural networks who want to shape how models are evaluated and improved.
- Function
- Development
- Estimated salary
- Est. $163k–245k/yr
- Estimated for a senior role, ~6 yrs experience (typical for the level), United States. Not published by the employer.
- Work mode and location
- On-Site, Palo Alto, CA
Job description
Overview
You will work on the most critical post-training and reinforcement learning challenges at any given time — including reward modeling, preference optimization (RLHF/DPO), and RL for improving reasoning, truthfulness, and real-world capabilities.
Roles and responsibilities
- Design and run rigorous experiments that turn research ideas into measurable gains in model capability
- Improve model recipes through data quality, deduplication, and mixture experiments
- Define what makes RL data and rewards good, including grader design and preventing reward hacking
- Advance training science, from architecture and scaling experiments to post-training recipes for coding and computer-use agents
- Build evals and targeted tasks that expose model weaknesses and guide where the team invests next
- Partner with engineers to take promising results from small experiments to frontier-scale training runs
Skills required
Top skills
- Post-training
- Reinforcement learning
- Rust
- C++
All skills (8)
- Large model training
- Reward modeling
- PyTorch
- JAX
- Python
- RLHF
- DPO
- Evals
Qualifications
- Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++
- Experience training large models (e.g., pre-training, post-training, fine-tuning, or RL training of neural networks with 1B+ parameters)
Nice to have
- You believe truth-seeking AI is the most important and challenging problem
- You are obsessed about building incredibly useful models through post-training and RL techniques
- You are a power user of AI models and eager to push the boundaries of what’s possible with reinforcement learning and alignment methods
- If you previously worked on post-training, RLHF, or trained models used by millions of people it’s a big plus, but relevant experience is not required
- You take pride in your work and thrive in meritocratic environments
Other details
$220,000 - $357,000 USD
Base salary is just one part of our total rewards package at SpaceXSI, which also includes equity, comprehensive medical, vision, and dental coverage, access to a 401(k) retirement plan, short & long-term disability insurance, life insurance, and various other discounts and perks.
Company info
About xAI
SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more