MLOps Engineer / Developer

RoundCircle; Bengaluru; On-site; INR 2,200,000 - 4,000,000; Full time

Job summary

RoundCircle is looking for a hands-on MLOps Engineer/Developer to build and operate production-grade ML and GenAI infrastructure. You will work closely with AI/ML teams to take models from experimentation to production through robust pipelines, CI/CD, model serving, monitoring, and cloud deployment.

The ideal candidate should have strong experience with Python, Jenkins, Azure, Databricks, FastAPI, Docker, Kubernetes/AKS and MLflow, along with a good understanding of DevSecOps and production ML

Qualifications

• 4+ years in ML/AI engineering or DevOps with hands-on production MLOps pipeline experience.
• CI/CD tooling incl. Jenkins, Azure DevOps and GitOps concepts; Git and pre-commit workflows.
• Databricks ML pipelines (Delta Lake, Workflows, MLflow), PySpark for data processing.
• Model serving with FastAPI/Docker on AKS; exposure to vLLM and ONNX/TensorRT optimization.
• Cloud knowledge – Azure/AWS/GCP Storage and AI related services.
• Databases/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 multi-stage promotion.
• Deploy model-serving APIs on AKS using FastAPI and vLLM; optimize with ONNX/TensorRT.
• 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

Python

Jenkins

Azure

Databricks

FastAPI

Docker

Kubernetes

MLflow

AKS

ONNX/TensorRT

Observability

GitOps

PostgreSQL

Redis

ADLS Gen2

Tools

Jenkins

Azure

Databricks

FastAPI

Docker

Kubernetes

MLflow

AKS

Prometheus/Grafana

ONNX/TensorRT

Job description

We are looking for a hands‑on MLOps Engineer / Developer to build and operate production‑grade ML and GenAI infrastructure. You will work closely with AI/ML teams to take models from experimentation to production through robust pipelines, CI/CD, model serving, monitoring, and cloud deployment

The ideal candidate should have strong experience with Python, Jenkins, Azure, Databricks, FastAPI, Docker, Kubernetes/AKS and MLflow, along with a good understanding of DevSecOps and production ML systems.

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.
• Cloud knowledge – Azure/AWS/GCP Storage, AI related services.
• Databases and storage: PostgreSQL, Redis, ADLS Gen2.
• Understanding of containerization, Helm, and infrastructure automation.

Good 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.