MLOps / AI Infrastructure Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a MLOps / AI Infrastructure Engineer based in India.

As an MLOps / AI Infrastructure Engineer, you will build and operate the systems that power production-scale machine learning and generative AI workloads. You will work at the intersection of software engineering, data science, cloud infrastructure, and AI research. Your work will span model deployment, serving architectures, automated ML pipelines, and infrastructure optimization. You will help turn experimental models into reliable, scalable, and low-latency production services. A key part of the role will be optimizing GPU and cloud resources to support demanding AI workloads efficiently. You will collaborate closely with data scientists and AI researchers in a technically challenging and fast-moving environment. This is an opportunity to have a direct impact on the reliability, performance, and scalability of modern AI systems.

Accountabilities:

• Architect, build, and maintain scalable model deployment and serving pipelines for LLMs, deep learning models, and predictive analytics workloads.
• Develop production-grade model-serving architectures using technologies such as Triton, Ray, BentoML, or comparable platforms.
• Build and automate CI/CD pipelines covering data ingestion, feature management, model training, validation, deployment, and monitoring.
• Design and maintain reliable ML infrastructure capable of supporting large-scale AI and generative AI workloads.
• Manage containerized workloads and orchestration platforms, including Kubernetes, across cloud environments.
• Monitor GPU and CPU cluster utilization and identify opportunities to improve performance, availability, and resource efficiency.
• Optimize cloud infrastructure and compute expenditure for resource-intensive AI workloads.
• Partner closely with data scientists and AI researchers to transition experimental models into resilient, scalable, low-latency production services.
• Contribute to infrastructure automation, observability, reliability, and continuous improvements across the ML platform.

Requirements:

• 4-8 years of professional experience in cloud infrastructure, DevOps, backend engineering, MLOps, or a closely related engineering discipline, with significant exposure to ML systems.
• Strong proficiency in Python and hands-on experience with Docker, Kubernetes, and Terraform.
• Practical experience working with cloud platforms and managed AI/ML services such as AWS Bedrock, Amazon SageMaker, Google Cloud Vertex AI, or equivalent technologies.
• Solid understanding of machine learning infrastructure, model deployment, model serving, and production ML lifecycle management.
• Hands-on familiarity with vector databases such as Pinecone, Milvus, Qdrant, or similar technologies.
• Experience with LLM orchestration frameworks and modern generative AI infrastructure.
• Understanding of CI/CD, infrastructure-as-code, containerization, monitoring, and production reliability practices.
• Strong problem-solving skills and the ability to troubleshoot complex infrastructure and performance challenges.
• Comfortable collaborating with data scientists, AI researchers, software engineers, and other technical stakeholders.
• Bachelor's degree in Computer Science, Engineering, or a related technical field is preferred.

Benefits:

• Annual compensation of INR 1,800,000-2,500,000.
• Full-time employment opportunity.
• Remote working arrangement with flexibility to work remotely from India.
• Opportunity to work on large-scale machine learning and generative AI infrastructure.
• Exposure to modern AI/ML technologies, cloud platforms, GPU infrastructure, and model-serving systems.
• Significant technical ownership across deployment, automation, scalability, and infrastructure optimization.
• Collaborative environment working closely with AI researchers, data scientists, and engineering teams.
• Opportunity to develop expertise in rapidly evolving MLOps and AI infrastructure technologies.