ML-OPS / PLATFORM ENGINEER

Responsibilities

• Designed, deployed, and operated enterprise-grade MLOps/GenAI platforms across AWS and Azure, leveraging AWS Bedrock, SageMaker, Azure OpenAI, Azure AI Foundry, model serving, embeddings, RAG, vector databases, AI gateways, guardrails, and agentic frameworks.
• Built and automated cloud-native ML infrastructure using Terraform, Kubernetes (EKS/AKS/OpenShift), Docker, GitHub Actions, Azure DevOps, Jenkins, GitOps, and ArgoCD, enabling scalable model deployment, CI/CD, versioning, and release management.
• Implemented secure and highly available ML/AI platforms using AWS IAM, Azure IAM/RBAC, VPC/VNet, Key Vault, Secrets Manager, API Gateway, load balancers, ingress controllers, service mesh, autoscaling, and multi-account/subscription architectures.
• Developed and operationalized ML/GenAI workloads using Python, REST APIs, microservices, MongoDB, PostgreSQL, Redis, and vector databases, implementing model evaluation, prompt engineering, state management, caching, and high-throughput inference capabilities.
• Monitored, troubleshot, and optimized production ML/AI workloads using observability, logging, monitoring, SRE practices, performance tuning, resiliency, disaster recovery, and cost optimization, while collaborating with application, platform, infrastructure, and security teams.

Skills

• MLOps
• AWS/Azure
• Kubernetes
• Docker
• Python
• Terraform
• CI/CD
• GenAI/LLM
• RAG
• Bedrock/Azure OpenAI
• Vector DB
• Observability