Software Engineer, Productivity - Inference Runtime
Core
Building and hardening CI/CD infrastructure, release tooling, and validation systems for large-scale AI inference engines to ensure reliability, performance, and safety of model deployments.
Role type
Senior IC Release Engineering / Developer Productivity Engineer
Builds
Automated deploy gates, validation workflows, observability tools, and release automation for inference systems
Domain
AI Infrastructure / Large-scale Inference Systems
Deliverable
production ML models | infrastructure
Required skills
CI/CD systems, testing infrastructure, release engineering, automation, distributed systems debugging, Python, infrastructure reliability, canary deployments, failure triage
Preferred skills
C++, inference engine internals, GPU scheduling, performance optimization, cross-functional partnership
Technologies
Python, C++, CI/CD pipelines, distributed systems
Responsibilities
Evolve tooling for deploy gate validation, harden CI/testing infrastructure, reduce flaky failures, build automation for failure triage, improve observability and rollout safety, partner with inference teams to reduce developer friction
Seniority
Senior, hands-on IC