Staff Engineer, RL & AI Alignment

SpaceXAI; Palo Alto (CA); On-site; USD 180,000 - 600,000; Full time

Benefits offered by this job

Equity

Medical coverage

Dental coverage

Vision coverage

401(k)

Disability Insurance

Life Insurance

Perks and discounts

Job summary

xAI is seeking a bold engineer to tackle the most critical post-training and reinforcement learning challenges, including reward modeling and preference optimization (RLHF/DPO). The role focuses on enhancing reasoning, truthfulness, and real-world capabilities of our AI systems.

You will join a hands-on, meritocratic team that values initiative, high-quality work, and clear communication, with a strong emphasis on engineering excellence and knowledge sharing.

Qualifications

• Belief that truth-seeking AI is critical to progress.
• Passion for building useful models through post-training and RL.
• Power user of AI models; push boundaries of RL and alignment.
• Experience with RLHF/DPO is a plus but not required.
• Prides in work and thrives in meritocratic environments.

Responsibilities

• Tackle the most critical post-training and RL challenges at any given time.
• Work on reward modeling and preference optimization (RLHF/DPO).
• Improve reasoning, truthfulness, and real-world capabilities of models.

Skills

Truth-seeking AI

Post-training & RL techniques

AI model proficiency

Meritocratic mindset

Strong communication skills

Job description

xAI is seeking a bold engineer to tackle the most critical post-training and reinforcement learning challenges, including reward modeling and preference optimization (RLHF/DPO). The role focuses on enhancing reasoning, truthfulness, and real-world capabilities of our AI systems.

You will join a hands-on, meritocratic team that values initiative, high-quality work, and clear communication, with a strong emphasis on engineering excellence and knowledge sharing.