Generative AI architecture and Python expertise define this engineering role, focused on scalable products and cloud-native solutions within Agile delivery.
You will lead and contribute to AI products, pilots, and solutions using Python, React, and AWS tools. The work includes LLM pipelines, Agentic AI, MCP, Graph/RAG architectures, and prompt-based applications. You will collaborate with product managers, data scientists, and domain experts.
Key Responsibilities: Develop maintainable AI products, pilots, and solutions
Design scalable Gen AI architectures and LLM pipelines
Implement AWS cloud-native solutions using EKS and Lambda
Optimize performance through experimentation with Gen AI methods
Own delivery, milestones, metrics,
and reliability improvements
Requirements: 8+ years total experience and 6+ years engineering experience
1–2 years leading emerging technology or AI initiatives
Proficiency with GPT, Claude, Gemini, LLaMA, and prompt engineering
Experience with LangChain, LlamaIndex, and Amazon Bedrock
Bachelor’s or Master’s degree in a related technical field
Apply advanced Python, AWS, and Gen AI architecture skills to build scalable solutions and guide end-to-end Agile delivery.