Senior Devops - F/H/NB
Core
Optimizing AI model inference latency and performance, managing production deployment and hosting, and scaling infrastructure to handle thousands of simultaneous requests.
Role type
Senior DevOps Engineer (AI/ML Inference)
Builds
Scalable, low-latency AI inference services for video game titles
Domain
Video Games / AI/ML Infrastructure
Deliverable
production ML models
Required skills
Kubernetes production management, Python, Linux, shell scripting, observability pipelines, gRPC, HTTP/2, distributed systems, infrastructure as code
Preferred skills
Rust, large-scale matchmaking systems, low-latency online multiplayer constraints
Technologies
Triton Inference Server, vLLM, TensorRT-LLM, Kubernetes
Responsibilities
Optimize AI model inference to reduce latency, ensure production deployment and hosting, manage and optimize capacity for high concurrency, pilot and control infrastructure costs (GPU, cloud), collaborate with Data Science teams on training-to-production transitions, maintain dedicated ML infrastructure (servers, specialized resources), continuously improve inference system performance and reliability
Seniority
Senior, hands-on IC
