Specialist in machine learning engineering
Core
Build, operate, and scale infrastructure for advanced AI services, focusing on LLM inference, model serving, and vector databases.
Role type
Senior IC machine learning infrastructure engineer (SRE)
Builds
Resilient AI infrastructure including multi-tenant LLM inference, model-serving, VectorDB/RAG, and Model Context Protocol (MCP) platforms
Domain
Cloud-native distributed systems and machine learning infrastructure
Deliverable
production ML models
Required skills
Python, Go, Java, Kubernetes, Prometheus, Grafana, Splunk, OpenTelemetry, AWS/Azure/GCP, vLLM, Ray, Milvus, Pinecone, Redis
Preferred skills
LLM inference frameworks (TensorRT-LLM, KServe), GPU orchestration, RAG pipelines, chaos engineering
Technologies
Kubernetes, Prometheus, Grafana, Splunk, OpenTelemetry, vLLM, Ray, Milvus, Pinecone, Redis, AWS, Azure, GCP
Responsibilities
Operate and optimize multi-tenant LLM inference and model-serving platforms; Establish and monitor SLOs/SLIs and observability dashboards; Develop automation for deployment rollouts and self-healing systems; Optimize GPU utilization and inference performance; Lead complex production incident responses and root-cause investigations; Collaborate with AI researchers and platform teams on production readiness
Seniority
Senior, hands-on IC