Model Serving Engineer

Highlights

• Turn NEXUS tabular foundation model into reliable production system.
• Tackle unique inference challenges differing from traditional LLM serving.
• Define architecture for distributed inference across varied environments.

What they offer

• Competitive compensation with salary and equity
• Comprehensive health coverage for you and dependents
• Paid parental leave for all new parents
• Relocation support to join an office location

Ideal candidate

Performance-obsessed backend engineer who loves distributed systems and low-level optimization, excited to bridge research and production to scale novel tabular foundation models.

Requirements

• Bachelor's or Master's in Computer Science, Engineering or related field or equivalent experience
• 5+ years in model serving, ML infrastructure or closely related backend engineering
• Deep expertise in Python concurrency including GIL, multithreading, thread safety and multiprocessing
• Experience building asynchronous and message-driven systems
• Experience with high-performance, large-scale distributed systems
• Ability to read and reason about ML models at computational level including batching and memory
• Experience profiling and optimizing performance across CPU, memory, I/O and ideally GPU