Job Description

Description:

Architect and design end-to-end GenAI/LLM solutions leveraging AWS services such as Amazon Bedrock, SageMaker, Lambda, ECS/EKS, and S3
Lead deployment of LLMs into production environments, ensuring scalability, low latency, cost-efficiency, and reliability
Design and build Agentic AI systems — multi-agent orchestration, tool-calling, autonomous task planning, and agent-to-agent communication
Design and implement RAG (Retrieval-Augmented Generation) pipelines, vector databases, and prompt engineering strategies for enterprise use cases
Fine-tune, evaluate, and optimize LLMs for performance, cost, and accuracy
Develop robust, production-grade Python code for GenAI pipelines, APIs, and agent frameworks
Define best practices for LLMOps/MLOps, including CI/CD pipelines, model monitoring, versioning, and governance
Ensure solutions are secure, scalable, and compliant with enterprise architecture and data privacy standards
Collaborate with cross-functional teams (data engineers, ML engineers, product managers) to translate business requirements into technical architecture
Evaluate emerging GenAI/Agentic AI tools, frameworks, and AWS services, and provide recommendations for adoption
Mentor engineering teams on GenAI, Agentic AI, and AWS architecture best practices.
Create technical documentation, architecture diagrams, and present solutions to technical and non-technical stakeholders