Senior AI Platform Engineer

ОписаниеYou will own the infrastructure that serves our large language models in production: the serving stack, the GPUs behind it and the API layer in front of it. The systems are live and used every day; the engineering discipline around them - capacity planning, repeatable deployment, monitoring - is yours to build. ОтговорностиOwn the LLM serving stack in production: engine configuration, model rollout and version upgradesTune inference for latency, throughput and cost - batching, caching, parallelism, quantization - and prove each change with measurementsPlan GPU capacity and produce the numbers behind model and hardware decisionsOwn the API layer in front of the models: authentication, rate limits, routing and failover, usage meteringBuild the delivery layer: CI/CD, reproducible deployments, infrastructure as code, alerting and dashboardsOperate what you build: diagnose out-of-memory, startup and performance failures, and write the post-mortemKeep a model and service registry, so nothing critical depends on one machine or one person Изисквания5+ years in production engineering, with hands-on ownership of GPU inference workloadsHands-on experience with vLLM, SGLang, TGI or TensorRT-LLM: real configurations, real incidents, real fixesYou can quote latency, throughput and cache-hit numbers from your own work, and explain what moved themWorking knowledge of transformer internals: attention, KV cache, prefill versus decode, mixture-of-experts routing, quantizationStrong Python, including reading engine and model source and patching around a bugLinux fluency: systemd, Docker, nginx or HAProxy, GPU drivers, monitoringPreferred QualificationsGPU profiling with nsys or ncu; model-flops-utilisation reasoning.Multi-node inference and interconnect experience (NVLink, NVSwitch, InfiniBand, RoCE).Introducing CI/CD and infrastructure as code into a hand-rolled environment.Rust or C++ for performance-critical services.Kubernetes experience, and a view on when it is worth it.Technical StackServing: vLLM, SGLang, CUDA toolingLanguages: Python; Rust or C++ for performance-critical workServices: Flask, FastAPI, nginx, HAProxyData: PostgreSQL, Redis, ClickHouse, a vector database, S3-compatible storageOperations: Docker, systemd, Prometheus, Linux