Specialist AI-platform engineering role with a leading financial-markets infrastructure organisation. The incumbent will design, scale and operate production AI and GPU platforms across on-premise and private or sovereign cloud settings. The mandate requires production MLOps or LLMOps, distributed model inference, Python, FastAPI, AsyncIO, gRPC, up-to-date serving runtimes, Kubernetes, Docker, Helm, NVIDIA GPU tooling, enterprise AI gateways, model failover, observability, guardrails, performance tuning and GitOps or CI/CD.
Responsibilities
design, scale and operate production AI and GPU platforms across on-premise and private or sovereign cloud environments.
production MLOps or LLMOps
distributed model inference
Python
FastAPI
AsyncIO
gRPC
contemporary serving runtimes
Kubernetes
Docker
Helm
NVIDIA GPU tooling
enterprise AI gateways
model failover
observability
guardrails
performance tuning
GitOps or CI/CD
📌 Lead Ai Platform Engineer Mumbai
🏢 Avant Garde
📍 Mumbai
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.