AI Engineer + ML ops

Zorba AI; Hyderabad; On-site; INR 1,800,000 - 3,600,000; Full time

Job summary

Zorba AI is hiring an experienced MLOps Engineer to build and operate ML pipelines that move AI/ML models from experimentation to production. You’ll manage CI/CD with Jenkins and Azure DevOps, and deploy model-serving APIs on AKS using FastAPI.

This hands-on role connects data science and enterprise deployment, requiring 4–6 years in ML/AI engineering or DevOps, strong Python (FastAPI) skills, Databricks ML pipelines, Docker/Kubernetes, and cloud familiarity (Azure/AWS/GCP).

Qualifications

• 4+ years in ML/AI engineering or DevOps with hands-on production MLOps pipeline experience.
• Proficient in Jenkins, Azure DevOps, GitOps concepts; Git and pre-commit workflows.
• Databricks ML pipelines (Delta Lake, Workflows, MLflow), PySpark data processing.
• Model serving: FastAPI, Docker, AKS; exposure to vLLM and ONNX/TensorRT optimization.
• Python (FastAPI, Pydantic, async), Bash, YAML/SQL scripting.
• Cloud knowledge – Azure/AWS/GCP Storage, AI related services.
• Databases and storage: PostgreSQL, Redis, ADLS Gen2.
• Understanding of containerization, Helm, and infrastructure automation.

Responsibilities

• Build end-to-end pipelines — data ingestion, training, evaluation, packaging, versioning, and deployment.
• Develop and maintain Jenkins CI/CD for Dev → QA → Production with multi-stage gates.
• Deploy model-serving APIs on AKS using FastAPI and vLLM; apply ONNX/TensorRT optimizations.
• Set up observability — drift detection, Prometheus/Grafana, Azure Monitor.
• Apply DevSecOps practices — Key Vault, Managed Identity, SonarQube, Trivy/Snyk.
• Application development – REST, WebSocket Frameworks using FastAPI

Skills

ML/AI engineering

DevOps

CI/CD tooling

Databricks ML

Model serving

Python

FastAPI

Cloud knowledge

PostgreSQL

Docker

AKS

ONNX/TensorRT

Education

B.E./B.Tech in CS/SE/Data Science

Tools

Jenkins

Azure DevOps

GitOps

Databricks

MLflow

Docker

AKS

FastAPI

ONNX/TensorRT

Job description

MLOps Engineer / Developer

Snapshot

Experience: 4–6 years in ML/AI engineering or DevOps

Reports To: MLOps Technical Lead / Manager, AIML

Education: B.E./B.Tech in CS, Software Engineering, or Data Science

About The Role

Build and operate the MLOps pipelines that take AI/ML and GenAI models from experimentation to production — packaging, CI/CD delivery, model serving, and monitoring. A hands-on engineering role bridging data science and enterprise deployment.

Key Responsibilities

• Build end-to-end pipelines — data ingestion, training, evaluation, packaging, versioning, and deployment.
• Develop and maintain Jenkins CI/CD for Dev → QA → Production promotion with multi-stage gates.
• Deploy model-serving APIs on AKS using FastAPI and vLLM; apply ONNX/TensorRT optimizations.
• Set up observability — drift detection (Evidently AI), Prometheus/Grafana, Azure Monitor.
• Apply DevSecOps practices — Key Vault, Managed Identity, SonarQube, Trivy/Snyk.
• Application Development – REST, WebSocket Frameworks using FastAPI

Must-Have Skills

• 4+ years in ML/AI engineering or DevOps with hands-on production MLOps pipeline experience.
• CI/CD tooling: CI tooling (UV, Ruff, Pyrefly), Jenkins (strong), Azure DevOps, GitOps concepts; Git and pre-commit workflows.
• Databricks ML pipelines (Delta Lake, Workflows, MLflow), Asset Bundles and PySpark for data processing.
• Model serving: FastAPI, Docker, AKS; exposure to vLLM and ONNX/TensorRT optimization.
• Python (strong — FastAPI, Pydantic, async), Bash, YAML/SQL scripting.
• Cloud knowledge – Azure/AWS/GCP Storage, AI related services.
• Databases and storage: PostgreSQL, Redis, ADLS Gen2.
• Understanding of containerization, Helm, and infrastructure automation.

Nice to Have

• Airflow, DVC, and experiment tracking (W&B / Comet ML).
• Terraform, KEDA, Azure APIM, and AAD RBAC configuration.
• LLM fine-tuning pipelines; Ray Serve or BentoML exposure.
• Groovy (Jenkinsfile).
• Manufacturing or semiconductor domain experience.

Skills: azure,ml,data science,fastapi,pipelines