Manager/Senior Manager - Lead AI Platform Engineer

Hiresquad; Mumbai City; On-site; INR 4,000,000 - 6,500,000; Full time

Job summary

Hiresquad in Mumbai seeks an AI Platform Engineer for its Innovation Lab to advance specialized AI platform engineering in a regulated financial context.

The role emphasizes MLOps/LLMOps, distributed inference, and GPU infrastructure across sovereign/private clouds and on-premise environments, with a focus on observability, guardrails, and CI/CD automation.

Qualifications

• Production MLOps/LLMOps experience required.
• 3+ years building production AI systems.
• Experience in GPU infrastructure, enterprise AI gateways, and observability.

Responsibilities

• Architect and scale production AI systems for mission-critical financial apps.
• Lead MLOps/LLMOps pipelines and distributed model inference.
• Engineer GPU infrastructure across cloud, on-prem, and private enviroments.
• Implement enterprise AI gateways, semantic routing, failover, and guardrails.
• Drive GPU performance tuning, production troubleshooting, and CI/CD automation.
• Collaborate with cross-functional teams to deliver secure, scalable AI innovation.

Skills

MLOps/LLMOps

Distributed inference

GPU infrastructure

Python

FastAPI

AsyncIO

gRPC

Kubernetes

Docker

Helm

NVIDIA GPU Operator

KEDA

Education

BE/BTech/MCA in Computer Science/IT/Data Science

Tools

vLLM

NVIDIA Triton

TensorRT

Ray Serve

Hugging Face TGI

llama.cpp

Job description

AI Platform Engineer Innovation Lab

Sector: Leading Financial Markets Infrastructure Organisation Location: Mumbai Experience: 6+ years Grade: Manager / Senior Manager

Role Overview

This is a specialist AIplatform engineering roledistinct from generic Data Science or application development. The position demands deep expertise in MLOps/LLMOps, distributed inference, and GPUbased AI infrastructure, within regulated financial environments.

Key Responsibilities

• Architect and scale production AI systems for missioncritical financial applications.
• Lead MLOps/LLMOps pipelines and distributed modelinference frameworks.
• Engineer GPU infrastructure across sovereign/private cloud and onpremise environments.
• Implement enterprise AI gateways, semantic routing, failover mechanisms, observability, and guardrails.
• Drive GPU performance tuning, production troubleshooting, and CI/CD automation.
• Collaborate with crossfunctional teams to deliver secure, scalable AI innovation.

NonNegotiable Requirements

• Education: BE/BTech/MCA in Computer Science, IT, Data Science, or related discipline.
• Experience: 68 years in software engineering or DevOps, including:
  
  • 3+ years of handson production MLOps/LLMOps and distributed inference.
  • 3+ years architecting and scaling production AI systems.
• Proven expertise in AIplatform engineering, distributed systems, GPU infrastructure.
• Handson proficiency with:
  
  • Languages/Frameworks: Python, FastAPI, AsyncIO, gRPC
  • Inference Platforms: vLLM, NVIDIA Triton, TensorRTLLM, Ray Serve, Hugging Face TGI, llama.cpp
  • Containers/Orchestration: Kubernetes, Docker, Helm, NVIDIA GPU Operator, KEDA
• Strong background in enterprise AI gateways, semantic routing, failover, observability, and guardrails.
• Expertise in GPU performance tuning, production troubleshooting, GitOps/CICD.