Sr. Model Engineer, RL Training Framework
xAIPalo Alto, CAposted 3h ago
- PayUSD / yr
- $180k – 400k
- Where
- Palo Alto, CA
- Posted
- Nov 4
- 3 hours ago
- Type
- Full-time
- Setup
- On-site
At a glance
Build and optimize the reinforcement learning training framework powering SpaceXSI’s large-scale model workloads, improving performance, scalability, and observability across the RL stack.
Summarized by AI from the original posting
What you'll do
- Design and implement systems backing reinforcement learning workloads
- Profile, debug, and optimize end-to-end training performance
- Improve scalability and observability of the reinforcement learning stack
Requirements
- 01Production-quality programming experience
- 02Experience training large models with 1B+ parameters
- 03Experience building, debugging, and optimizing large-scale distributed systems
- 04Experience with large-scale LLM training infrastructure
- 05Experience with RL numerics
- 06Strong knowledge of reinforcement learning techniques
- 07Ability to solve problems across the technology stack
Perks
Skills
Full description
SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.
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 compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next.
SR. MODEL ENGINEER, RL TRAINING FRAMEWORK
The RL infrastructure team is looking for an engineer to help develop our RL training framework.
RESPONSIBILITIES:
- Design and implement the systems backing all RL workloads at SpaceXSI, from small scale ablations to production training runs
- Profile, debug, and optimize end-to-end training performance
- Improve scalability and observability of the RL stack
BASIC 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)
PREFERRED SKILLS AND EXPERIENCE:
- Experience building, debugging, and optimizing efficiency of large-scale distributed systems
- Experience with large scale LLM training infrastructure
- Experience with RL numerics
- Strong knowledge of reinforcement learning techniques
- Comfortable diving into unfamiliar areas and solving problems at all levels of the stack
COMPENSATION AND BENEFITS:
$180,000 - $400,000 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.
SpaceXSI is an equal opportunity employer. For details on data processing, view our Recruitment Privacy Notice.