ROLE AND RESPONSIBILITIES
5–8 years of experience in software engineering, platform engineering,
DevOps, SRE, MLOps, or related infrastructure roles.
Strong hands-on experience with Kubernetes, including writing Kubernetes Operators and Custom Resource Definitions using frameworks such as Kubebuilder, Operator SDK, or equivalent.
Experience designing and operating cloud-native infrastructure on AWS, particularly Amazon EKS, EC2, S3, ECR, IAM, VPC, and CloudWatch.
Experience deploying and operating machine learning, deep learning, or generative AI models in production.
Experience running and troubleshooting GPU-accelerated workloads on Kubernetes, with an understanding of GPU scheduling, utilization, memory constraints, and performance.
Familiarity with model-serving frameworks such as KServe, NVIDIA Triton Inference Server, vLLM, Ray Serve, TorchServe, or equivalent technologies.
Robust programming experience in Go or Python, with experience building production-grade APIs, controllers, or distributed backend services.
Experience with containers, Helm, CI/CD, infrastructure as code, and observability tools such as Prometheus, OpenTelemetry, and Grafana.
Solid understanding of Linux, networking, storage, security,



and distributed-system fundamentals.
Strong debugging, problem-solving, communication, and cross-functional collaboration skills.

REQUIRED SKILLS (explicitly call out must-have and nice-to-have skills expectations)
Experience building an MLOps platform, AI infrastructure platform, internal developer platform, or Kubernetes-based enterprise product.
Experience writing GPU kernels or performance-critical code using CUDA C/C++ or Triton is a plus.
Experience with large language model serving, distributed inference, batching, quantization, or inference-performance optimization.
Experience with NVIDIA GPU Operator, MIG, GPU time-slicing, Energetic Resource Allocation, or similar GPU-management technologies.
Familiarity with AWS Inferentia, Trainium, SageMaker, or Amazon Bedrock.
Experience operating AI platforms across hybrid-cloud, on-premises, air- gapped, or multi-tenant settings.

Pay: ₹1,000,000.00 - ₹3,000,000.00 per year

Application Question(s)
Immediate to 15 days preferred

Experience
MLOps: 5 years (Preferred)

Work Location: In person

📌 Mlops Engineer Coimbatore (India)
🏢 Sama
📍 India