AWS Gen AI Cloud Platform Engineer
Exp: 5+ years
Location – Chennai
Key Responsibilities
Cloud Architecture Engineering (AWS):
Design, build, and operate scalable, secure, highly available AWS workloads (compute, networking, storage, data, serverless).
Develop reference architectures and IaC modules aligned to best practices and guardrails.
DevOps Platform Automation
Implement CI/CD pipelines, automated testing, and
GitOps workflows. Own Infrastructure as Code (Terraform/CDK/CloudFormation), configuration management, and environment provisioning across dev/test/prod.
Observability Reliability
Set up logging, metrics, tracing, and SLOs using CloudWatch.
Drive incident response, postmortems, capacity planning, and reliability improvements.
Security Compliance
Embed security-by-design (IAM, KMS, Secrets Manager), enforce least privilege, and implement threat detection and vulnerability management.
Support compliance needs (e.g., SOC2, ISO 27001, GxP) via policy-as-code and automated controls.
Cost Management FinOps
Monitor and optimize cloud spend with tagging, budgets, RI/SP management, right sizing, and usage analytics. Advise teams on cost efficient architectures.
Data Integration
Build data pipelines (AWS Glue, Step Functions, Lambda, EventBridge) and API integrations (API Gateway, AppSync, ALB/NLB) to support AI workloads and product features.
AI Platform Enablement (Bedrock, GenAI)
Design and operate Amazon Bedrock integrations, model access patterns, prompt and retrieval pipelines, and RAG architectures using AWS native and open tooling.
Agentic AI Orchestration
Implement agentic workflows (tool use, planning, memory) with frameworks (LangChain, AWS Agents for Bedrock) and secure tool adapters (search, code, data).
Manage observation and safety layers.
MLOps For Foundation Models
Establish versioning, evaluation, governance, and rollout practices for prompts, datasets, embeddings, and model variants.
Automate offline/online evaluation, A/B tests, and canary releases.
Cross Functional Collaboration
Partner with product, data science, security, and compliance to translate requirements into robust cloud and AI solutions.
Provide technical documentation and knowledge sharing.
Skills: python,generative ai,aws,ci/cd,genai,agentic,amazon web services (aws),devops,aws engineer