LLM Ops Engineer

We're Hiring | LLM Ops Engineer (Infrastructure & Performance)
We are looking for a Junior AI MLOps Engineer to join our Data Science & AI/ML team in Bangalore. If you're passionate about AI infrastructure, LLM deployment, cloud optimization, and building reliable, scalable ML systems, we'd love to hear from you!
📍 Location: Bangalore – On-site💼 Experience: 1–2 Years🏢 Department: Data Science & AI/ML☁️ Primary Cloud: AWS
Key Responsibilities
Evaluate AWS hosting options such as Lambda, EC2, SageMaker, and Bedrock to optimize cost and performance for LLMs and ML models.
Track and analyze cost-per-inference, latency, throughput, and resource utilization.
Build and maintain CI/CD pipelines for model testing, containerization, and deployment.
Deploy and manage ML workloads using Docker, Kubernetes, and AWS services such as EKS and ECS.
Monitor model performance, API health, infrastructure reliability, and model drift.
Optimize CPU/GPU utilization, availability, scalability, and cloud infrastructure costs.
Collaborate with Data Science teams to deploy models as scalable, version-controlled microservices.
Required Skills
1–2 years of hands-on experience in MLOps, DevOps, or Backend Engineering, preferably working with ML infrastructure.
Strong proficiency in Python.
Experience with Docker and Kubernetes.
Practical knowledge of AWS services, including Lambda, EC2, S3, and SageMaker.
Understanding of CI/CD pipelines, model deployment, monitoring, and versioning.
Familiarity with FastAPI or Flask and REST API integration.
Basic understanding of the ML lifecycle, model monitoring, and feature stores.
Analytical skills to evaluate infrastructure performance and cost efficiency.
Good to have: Exposure to AWS Bedrock, LLM deployment, and AI infrastructure cost optimization.
Education
Bachelor's degree in Computer Science, Information Technology, or a related technical field.

Work arrangement
No