Required SkillsMLOps & Model DeploymentCloud Platforms - AWS/Azure/GCPDocker, Kubernetes, CI/CDMonitoring & LLM OpsKey ResponsibilitiesDeploy and Manage AI/LLM Models in production environments for B-Informative IT Services clients.Build and maintain MLOps Pipelines for training, inference, versioning, and rollback of AI models.Work with Docker, Kubernetes, and Terraform to create scalable, reliable AI infrastructure.Set up Monitoring, Logging, and Alerting for model performance, drift, latency, and cost using tools like Prometheus, Grafana, MLflow.Optimize cloud resources on AWS, Azure, or GCP for AI workloads and inference costs.Automate CI/CD for ML models using Jenkins, GitHub Actions, or GitLab CI.Collaborate with Data Science and Engineering teams to productionize research models.Ensure security, compliance, and reliability of AI systems and data pipelines.Ideal Candidate3-5 years experience in DevOps, SRE, or MLOps with exposure to AI/ML workloads.Hands-on with Python, Docker, Kubernetes, and Cloud services.Experience deploying LLMs, RAG pipelines, and Vector Databases.Familiarity with MLflow, Kubeflow, Airflow, and Model Serving frameworks.Strong troubleshooting and automation mindset.Good understanding of API deployment, load balancing, and GPU optimization.Self-driven and comfortable working in a Fully Remote setup.Why Join?Run production AI at scale for B-Informative IT Services across industries.₹15 - 17K/Year + fully remote flexibility + access to cloud and GPU resources.Work on cutting-edge LLM, GenAI, and enterprise AI deployments.Bridge the gap between Data Science and Production Engineering.Growth path into Lead MLOps Engineer or AI Platform Architect roles.

AI Operations Engineer

Emma

Requirements and responsibilities

Skills wanted:

Language(s) required:

Sekar Selvaraj

Sekar Selvaraj

About B-Informative IT Services Pvt. Ltd:

www.biitsinc.com/

Admin access needed