Gen AI Engineer – RAG Systems & AI Transformation

Job Description

Summary

We are seeking a highly skilled and forward-thinking GenAI Engineer to join our AI innovation team. This role is ideal for someone with deep technical expertise in Generative AI, a strong foundation in Python programming, and a passion for driving enterprise AI transformation.

You will be instrumental in designing, developing, and deploying advanced Retrieval-Augmented Generation (RAG) systems. You’ll also play a pivotal role in enabling our internal workforce to embrace and adopt AI technologies.

Your role in our mission
• Enable the workforce to adopt an AI first strategy by leveraging AI code assistance tools
• Architect and implement scalable RAG systems using Python and modern GenAI tools.
• Build custom pipelines for document ingestion, chunking strategies, and embedding generation. Working knowledge in LlamaIndex is preferable.
• Have a deep knowledge in using AI augmented tools like GitHub Copilot. Experience in developing custom extensions
• Evaluate and implement different embedding models (OpenAI, Azure OpenAI, Cohere, etc.) and chunking strategies (fixed-size, semantic-aware, overlap-based).
• Create and optimize indexing strategies (vector, hybrid, keyword-based, hierarchical) for performance and accuracy.
• Work with Azure AI Services, particularly Azure Cognitive Search and OpenAI integration, to deploy end-to-end AI applications.
• Collaborate closely with cross-functional teams including data engineers, product managers, and domain experts.
• Conduct AI enablement sessions, workshops, and hands-on labs to upskill internal teams on GenAI usage and best practices.
• Participate in code reviews, contribute to best practices, and ensure the reliability, scalability, and maintainability of AI systems.

What we’re looking for
• 5+ years of experience in software engineering, with strong expertise in Python.
• Proven track record of building and deploying RAG-based GenAI solutions.
• Hands-on experience with LlamaIndex, LangChain, or equivalent frameworks.
• Familiarity with prompt engineering, prompt tuning, and managing custom Copilot extensions.
• Strong understanding of LLMs, vector databases (like FAISS, Pinecone, Azure Cognitive Search), and embedding techniques.
• Solid knowledge of Azure AI, cloud deployment, and enterprise integration strategies.
• Proficiency with version control and collaborative development using GitHub.

What you should expect in this role
• Enable the workforce to adopt an AI first strategy by leveraging AI code assistance tools
• Architect and implement scalable RAG systems using Python and modern GenAI tools.
• Build custom pipelines for document ingestion, chunking strategies, and embedding generation. Working knowledge in LlamaIndex is preferable.
• Have a deep knowledge in using AI augmented tools like GitHub Copilot. Experience in developing custom extensions
• Evaluate and implement different embedding models (OpenAI, Azure OpenAI, Cohere, etc.) and chunking strategies (fixed-size, semantic-aware, overlap-based).
• Create and optimize indexing strategies (vector, hybrid, keyword-based, hierarchical) for performance and accuracy.
• Work with Azure AI Services, particularly Azure Cognitive Search and OpenAI integration, to deploy end-to-end AI applications.
• Collaborate closely with cross-functional teams including data engineers, product managers, and domain experts.
• Conduct AI enablement sessions, workshops, and hands-on labs to upskill internal teams on GenAI usage and best practices.
• Participate in code reviews, contribute to best practices, and ensure the reliability, scalability, and maintainability of AI systems.