Model Engineer, Post-Training & RL
SpaceX Super Intelligence
Palo Alto, CA3h agovia LinkedIn
This job at a glance
- Who can apply
- New grads, no experience needed
- Must know
- PythonC++RustPyTorch
- Work
- On-site in Palo Alto
- Pay
- Not stated by the employer.
- Skill demand
- Python18%C++12%PyTorch5%Rust4%of 99 similar entry-level jobs posted in the US this week
- Listed
- Nov 10, 2026 · still open
Sign in free to see which of these skills your resume already shows.
About the Role
The Model Engineer, Post-Training & RL will work on critical post-training and reinforcement learning challenges, including reward modeling, preference optimization (RLHF/DPO), and RL for improving reasoning, truthfulness, and real-world capabilities.
Key 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 evaluations and targeted tasks that expose model weaknesses and guide team investment.
- Partner with engineers to scale promising results from small experiments to frontier-scale training runs.
Requirements & Tech Stack
- Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++.
Qualifications
- 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.
- You take pride in your work and thrive in meritocratic environments.