Model Serving Engineer

📋 Description

• Optimize Python inference under real concurrency constraints.
• Collaborate with research/infrastructure on hardware tradeoffs.
• Define architecture for distributed inference and async execution.
• Own the Triton serving layer for NEXUS in production.
• Build observability tooling for latency, throughput, resource efficiency.
• Resolve cross-environment serving challenges across scale, isolation, reliability.

🎯 Requirements

• Bachelor's or Master's in CS/Engineering (or equivalent)
• 5+ years in model serving, ML infra, or backend engineering
• Deep expertise in Python concurrency (GIL, threading, multiprocessing)
• Experience building asynchronous and message-driven systems
• High-performance, large-scale distributed systems
• Ability to read and reason about ML model compute, batching, memory, inference

🎁 Benefits

• Competitive compensation with salary and equity
• Comprehensive health coverage for you and dependents
• Paid parental leave for all new parents
• Relocation support for employees joining the team
• Mission-driven, low-ego culture supporting diversity and action