Machine Learning Model Operations ( MLOps)

EXL; Bengaluru; Hybrid; INR 2,500,000 - 4,000,000; Full time

Job summary

EXL in Bengaluru is seeking an hands-on MLOps Engineer with 4–10 years of experience to deploy and operationalize ML models in production across cloud and on‑prem environments. You will own end-to-end ML lifecycle, from ingestion to deployment, while coordinating closely with cross‑functional teams.

The role emphasizes production monitoring, observability, and rollback strategies, with strong emphasis on CI/CD, containerization, and scalable pipelines. Prior Banking domain exposure is a plus.

Qualifications

• Hands-on MLOps engineer with 4–10 years of experience deploying and operationalizing ML models in production.

Responsibilities

• Deploy ML models to production on cloud and on-premises environments.
• Manage the ML model lifecycle, including monitoring, logging, and rollback strategies.
• Collaborate with Model Development, Data Engineering, and Infrastructure teams.

Skills

Python

PySpark

ML deployment

ML lifecycle management

Cloud & on-prem

Collaborative skills

Tools

Snowflake

Databricks

Jenkins

GitHub Actions

GitLab CI/CD

Docker

Kubernetes

MLflow

Model Registry

Airflow

Job description

We are looking for hands-on MLOps Engineers with proven 4 -10 years of experience in deploying and operationalizing ML models in production and managing the ML model lifecycle across cloud and on-premises environment in Banking Domain.

Key Skills & Hand-on Experience:

• Python & PySpark
• AWS Cloud (SageMaker, EC2, S3, Lambda, EKS, or similar services), Good to have : Azure, GCP
• Snowflake, Databricks
• CI/CD Pipelines (Jenkins, GitHub Actions, GitLab CI/CD)
• Docker & Kubernetes
• GitHub, GitLab, Release Management
• MLflow, Model Registry, Model Deployment, Airflow, Scheduled Batch Scoring
• Production Monitoring, Logging, Alerting, Observability, Troubleshooting & Rollback Strategies
• Code conversion/refactoring, UAT testing, PIV, and production release activities
• Containerizing and deploying ML predictive models on cloud and on-premises production environments
• Building automated data ingestion pipelines with DQ checks, and orchestrating scoring pipelines with output DQ checks.
• Collaborating with cross-functional teams, including Model Development, Data Engineering, Infrastructure .