Key Responsibilities
- Design and develop scalable AI/GenAI solutions on AWS and Azure.
- Build and deploy RAG applications, AI agents, LLM-based APIs, and intelligent automation solutions.
- Develop serverless and event-driven AI applications using AWS and Azure native services.
- Integrate LLM applications with AWS Lambda and Azure Functions.
- Design scalable distributed and event-driven cloud architectures.
- Develop production-grade AI services using Python.
- Build REST APIs using FastAPI, Flask, or similar frameworks.
- Implement CI/CD pipelines and Infrastructure-as-Code for cloud workloads.
- Implement monitoring, logging, security, governance, and cost optimization.
- Work with enterprise applications, APIs, databases, and cloud platforms.
- Participate in architecture discussions and provide technical guidance to engineering teams.
Technical Skills
Generative AI & LLMs
- Amazon Bedrock and/or Azure OpenAI.
- Azure AI Foundry and Azure AI Search.
- Amazon SageMaker and/or Azure Machine Learning.
- LLMs, embeddings, vector databases/search, and RAG architecture.
- Prompt engineering, AI agents, and agent frameworks.
- LLM evaluation, observability, guardrails, and responsible AI.
- Serverless RAG and event-driven GenAI workflows.
Model Context Protocol & AI Agents
- Understanding of Model Context Protocol (MCP) and experience building or configuring MCP servers.
- Experience developing AI agents using Bedrock Agents, Agent Core, or similar frameworks.
Python & Application Development
- Strong Python programming skills.
- Experience with Lambda handlers and boto3.
- Experience with LangChain and/or LlamaIndex.
- REST API development using FastAPI, Flask, or equivalent.
- Knowledge of JSON, REST APIs, authentication, OAuth/OIDC, and API integrations.
- Experience with asynchronous programming and distributed systems.
Cloud, Serverless & DevOps
- Strong hands-on experience with AWS and Azure.
- Serverless development using Lambda, API Gateway, S3, DynamoDB, and Azure Functions.
- Docker, ECS, EKS, and/or Kubernetes.
- Infrastructure-as-Code using Terraform, AWS CDK/SAM, or Azure Bicep.
- CI/CD using GitHub Actions, GitLab, Jenkins, Azure DevOps, or equivalent.
- MLOps/LLMOps experience using MLflow, SageMaker, Azure ML, or similar platforms.
- Monitoring and observability using CloudWatch, Azure Monitor, Application Insights, OpenTelemetry, or similar tools.
Additional Requirements
- Minimum 5+ years of hands-on experience in Cloud and GenAI technologies.
- Experience delivering production-grade AI/GenAI applications.
- Strong troubleshooting, system design, and problem-solving skills.
- Experience using AI coding tools such as Amazon Q Developer, GitHub Copilot, Cursor, or Kiro.
- Strong understanding of software engineering principles, design patterns, and clean code.