Member of Technical Staff - Evaluation Infrastructure

Details

SpaceXAI's RL infrastructure team is looking for an engineer to help develop evaluation infrastructure for next-generation AI models. The role involves building reliable, efficient, and easy-to-use systems for running evaluations at scale and collaborating with modeling and evaluation teams.

Responsibilities

• Build highly reliable, efficient, and easy-to-use infrastructure that runs evaluations at scale.
• Collaborate closely with modeling and evaluation teams to develop new evaluations, maintain evaluation signal quality, and build internal tooling to support training next-generation models.
• Identify and resolve performance bottlenecks across the evaluation infrastructure stack, including inference, capacity fleet management, asynchronous evaluation orchestration, and related systems.

Requirements

Basic Qualifications

• Experience building, debugging, and optimizing large-scale distributed systems.
• Willingness to dive deep and solve difficult problems at all levels of the stack.

Preferred Skills and Experience

• Experience with large language model inference.
• Experience with GPU compute management, workload scheduling, and dynamic resource optimization.
• Experience developing interfaces for comparing models and evaluations.
• Strong communication, prioritization, and problem-solving skills.

Benefits

• Equity.
• Comprehensive medical, vision, and dental coverage.
• Access to a 401(k) retirement plan.
• Short- and long-term disability insurance.
• Life insurance.
• Various other discounts and perks.
• Equal opportunity employer.