Technical Project Lead / Architect / GenAI Lead – AWS Cloud & GenAI

Key Responsibilities :

• Lead the design, development, and deployment of GenAI projects leveraging Large Language Models (LLMs) on cloud platforms, primarily AWS.
• Architect and implement scalable, event-driven cloud-native solutions using AWS Lambda, SNS / SQS, Step Functions, and related services.
• Drive prompt engineering strategies including prompt versioning, optimization, and chain-of-thought design to enhance model performance.
• Oversee fine-tuning, embeddings, and conversational flow development to build intelligent, context-aware AI applications.
• Integrate and manage LLM APIs such as Azure OpenAI and other emerging models to deliver cutting-edge AI capabilities.
• Utilize vector databases (ElasticSearch, Open Search, or similar) for embedding-based search and Retrieval-Augmented Generation (RAG).
• Lead model evaluation efforts including output analysis, performance tuning, and quality benchmarking to ensure high standards.
• Collaborate with cross-functional teams including data scientists, engineers, and product managers to align AI solutions with business goals.
• Mentor and guide technical teams on best practices in GenAI development and cloud architecture.
• Stay abreast of the latest advancements in AI, cloud technologies, and LLM frameworks to continuously innovate and improve solutions.

Skills & Experience :

• Proven hands-on experience integrating Large Language Models (LLMs) into real-world applications.
• Strong programming skills in Python and experience with web frameworks such as FastAPI or Flask.
• Expertise in cloud architecture, particularly AWS services including Lambda, SNS / SQS, Step Functions, and event-driven design patterns.
• Deep knowledge of LLM APIs, with mandatory experience in Azure OpenAI; familiarity with other models like LLaMA is a plus.
• Experience working with vector databases such as ElasticSearch, Open Search, or other vector search engines.
• Proficiency in prompt engineering techniques including prompt versioning, optimization, and chain-of-thought design.
• Familiarity with LLM frameworks such as LangChain and LlamaIndex.
• Experience with embedding-based search and Retrieval-Augmented Generation (RAG) methodologies.
• Strong skills in model evaluation, including output analysis, performance tuning, and quality benchmarking.
• Excellent leadership, communication, and project management skills.