Lead/Senior Inference Engineer
Core
Build and operate production inference infrastructure powering advanced large language models and AI-driven professional applications.
Role type
Senior IC inference infrastructure engineer
Builds
Reliable, scalable model-serving platform
Domain
AI/LLM infrastructure
Deliverable
production ML models
Required skills
Kubernetes, distributed systems, model-serving infrastructure, inference optimization, observability, compliance frameworks, cost tracking, systems programming
Preferred skills
vLLM, TensorRT-LLM, Triton, SGLang, GPU-cluster capacity planning, multi-region/multi-cloud deployment, ISO 27001, Rust, Go, systems-level performance optimization
Technologies
Kubernetes, vLLM, TensorRT-LLM, Triton, SGLang, Rust, Go
Responsibilities
Build and maintain production-grade model-serving infrastructure; Implement and optimize inference techniques (batching, caching, quantization); Strengthen platform observability and monitoring; Develop operational and compliance foundations (ISO 27001); Establish cost-tracking and GPU-capacity contingency plans; Evaluate trade-offs between cost, latency, and reliability; Integrate new model releases into serving infrastructure; Establish engineering practices and tools; Collaborate with research, product, and engineering stakeholders; Mentor other engineers
Seniority
Senior, hands-on IC with mentorship