MLOps Engineer Mid-Senior · Full-time · Remote →

Thewebvale; Bhopal; Hybrid; INR 1,500,000 - 2,100,000; Full time

Benefits offered by this job

Remote-first

Bhopal studio hybrid days

Direct work with founder and senior 팀

Learning and tooling support

Portfolio feature

Job summary

TheWebVale is seeking an experienced MLOps Engineer to build and maintain production AI services infrastructure, including model serving, latency tracking, and automated deployments.

You will deploy open-weight models, embeddings, and prediction pipelines on GPU/CPU cloud instances, collaborating with AI engineers and backend developers for regular release cycles, ensuring low latency, high availability, and scalable operations.

Qualifications

• 6 things, one at a time. Keep scrolling.
• 01 / 06 Hold 3–5 years of software engineering or DevOps experience with dedicated MLOps focus.
• 02 / 06 Demonstrate strong proficiency with Docker, Linux system administration, and GPU drivers.
• 03 / 06 Show hands‑on experience serving models with vLLM, Hugging Face TGI, or FastAPI.
• 04 / 06 Understand model quantization formats, tensor parallelism, and batching mechanisms.
• 05 / 06 Possess experience building automated deployment workflows in GitHub Actions.
• 06 / 06 Communicate infrastructure reliability and capacity plans clearly to engineering leads.

Responsibilities

• Deploy and scale machine learning and LLM inference engines using vLLM, Triton, or Ollama.
• Build automated CI/CD deployment pipelines for model weights, embeddings, and prompt configs.
• Configure GPU hardware monitoring, memory allocation, and utilization alerts.
• Implement model versioning, rollback protocols, and blue‑green deployment strategies.
• Track inference latencies, token consumption rates, and error rates using Prometheus and Grafana.
• Optimize container images to reduce cold‑start latency and cloud server costs.

Skills

MLOps

Docker

vLLM

Python

CI/CD

Tools

Hugging Face TGI

FastAPI

Job description

You will build model serving infrastructure, latency tracking pipelines, and automated deployments for production AI services.

As an MLOps Engineer at TheWebVale, you will manage the operational lifecycle of AI models and inference engines. You will deploy open‑weight language models, embedding services, and prediction pipelines on GPU and CPU cloud instances for business client applications. You will collaborate closely with AI engineers and backend developers in our regular two‑to‑three week release intervals. You will ensure models are served with low latency, high availability, auto‑scaling, and predictable cloud expenditure.

MLOps

Docker

vLLM

Python

CI/CD

Your day to day

6 things, one at a time. Keep scrolling.

• Deploy and scale machine learning and LLM inference engines using vLLM, Triton, or Ollama.
• Build automated CI/CD deployment pipelines for model weights, embeddings, and prompt configs.
• Configure GPU hardware monitoring, memory allocation, and utilization alerts.
• Implement model versioning, rollback protocols, and blue‑green deployment strategies.
• Track inference latencies, token consumption rates, and error rates using Prometheus and Grafana.
• Optimize container images to reduce cold‑start latency and cloud server costs.

Requirements

6 things, one at a time. Keep scrolling.

• 01 / 06 Hold 3–5 years of software engineering or DevOps experience with dedicated MLOps focus.
• 02 / 06 Demonstrate strong proficiency with Docker, Linux system administration, and GPU drivers.
• 03 / 06 Show hands‑on experience serving models with vLLM, Hugging Face TGI, or FastAPI.
• 04 / 06 Understand model quantization formats, tensor parallelism, and batching mechanisms.
• 05 / 06 Possess experience building automated deployment workflows in GitHub Actions.
• 06 / 06 Communicate infrastructure reliability and capacity plans clearly to engineering leads.

What you get

• Remote‑first, with a Bhopal studio for hybrid days
• Real client products across many industries
• Direct work with the founder and senior team
• Learning and tooling support
• Your work featured in our public portfolio

How we hire

1. Intro chat

   A short call about what you want to work on and how you like to work.

2. Work review

   Walk us through projects, code or designs you are proud of.

3. Paid task

   A small paid task or pairing session, so both sides see the fit.

thewebvale.