Senior Model Engineer: Post-Training & RL

SpaceXSI; Palo Alto (CA); Sur place; USD 180 000 - 600 000; Plein temps

Avantages offerts par ce poste

Equity

Medical coverage

Vision

Dental

401(k) retirement plan

Disability insurance

Life insurance

Discounts and perks

Résumé du poste

SpaceXSI is seeking a Sr. Model Engineer to tackle post-training and reinforcement learning challenges for our Grok suite and X stack. You will refine reward models, optimize preferences (RLHF/DPO), and apply RL to improve reasoning and real-world capabilities.

You should have strong experience in Python, PyTorch, JAX, or C++, with a track record of training large models (1B+ parameters). A passion for truth-seeking AI and scalable ML systems is essential.

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).

Responsabilités

• Work on post-training and reinforcement learning challenges.
• Address reward modeling, preference optimization (RLHF/DPO), and RL for improving reasoning and truthfulness.

Connaissances

Production-quality code in Python, PyT

Training large models

Description du poste

SpaceXSI is seeking a Sr. Model Engineer to tackle post-training and reinforcement learning challenges for our Grok suite and X stack. You will refine reward models, optimize preferences (RLHF/DPO), and apply RL to improve reasoning and real-world capabilities.

You should have strong experience in Python, PyTorch, JAX, or C++, with a track record of training large models (1B+ parameters). A passion for truth-seeking AI and scalable ML systems is essential.