LLM AND (RAG OR Retrieval Augmented Generation) AND (LangChain OR LangGraph OR CrewAI OR AutoGen) AND Python AND Kubernetes, Agentic AI OR Multi Agent Systems OR Autonomous Agents OR AI Orchestration, (AWS Bedrock OR Azure OpenAI OR Vertex AI) AND (Kubernetes OR Docker) AND (Microservices OR Cloud Native)
AI Architecture & Engineering
- Define and own AI reference architectures for generative AI, agentic systems, and AI augmented applications
- Architect scalable solutions using LLMs, multi agent systems, orchestration frameworks, and AI pipelines
- Design AI platforms supporting model serving, prompt management, RAG, and workflow orchestration
- Establish architectural standards for performance, scalability, reliability, and cost efficiency Platform Engineering & Integration
- Build reusable AI components for LLM integration, vector search, embeddings, and inference services
- Enable secure and scalable deployment using Kubernetes, serverless platforms, and CI/CD pipelines
- Integrate AI capabilities into enterprise systems using APIs, SDKs, and event driven architectures
- Collaborate with QE teams to embed AI into test automation, test data generation, and intelligent validation
