AI Engineer Offline

We are seeking an experienced AI Engineer with a strong track record in building enterprise-grade applications to join our AI Modernization Program. This role focuses on designing and implementing the data and semantic intelligence backbone of AI assistants for software development teams, starting with a smart business analyst and extending to developer copilots.

You will lead the effort in transforming fragmented historical enterprise requirements, codebases, tickets, and documentation into a semantically searchable, AI-consumable knowledge base. The role combines LLM pipeline design, semantic search implementation, and unstructured data preparation with a deep understanding of enterprise development environments.

ABOUT THE PROJECT

Our client, a large-scale enterprise software provider, is undergoing a strategic transformation to integrate AI into development and QA workflows. Phase one involves creating an AI-powered Business Analyst assistant that understands product evolution and helps structure new feature planning. Subsequent phases will build a Developer Co-Pilot that translates requirements into implementation support and guidance.

You’ll be instrumental in architecting and developing accurate, context-aware AI agents (code assistant) that scale across teams using modern AI/ML practices like retrieval-augmented generation (RAG), knowledge graphs.

Key Responsibilities:

• Design and build semantic data pipelines to parse, index, and retrieve enterprise artifacts: user stories, documentation, tickets, and code history.
• Develop scalable embedding pipelines and integrate vector database architectures (ChromaDB, Azure Cognitive Search).
• Implement retrieval-augmented generation (RAG) pipelines tailored to enterprise development lifecycles.
• Create traceability models across product requirements, development artifacts, and business documentation.
• Collaborate with business analysts, architects, and developers to align AI capabilities with practical team needs.
• Ensure pipeline performance, scalability, and adaptability to enterprise-grade security and compliance needs.
  
   

Required Qualifications:

• 4+ years of applied experience in AI/ML, with a focus on enterprise data  use cases
• Proven experience in building semantic search systems, chunking strategies, and embedding-based retrieval
• Strong knowledge of Python
• Hands-on experience with vector stores (ChromaDB, Pinecone, Azure Cognitive Search)
• Deep familiarity with document processing, especially ticketing systems (Jira, ADO) and PDF, tables, pictures parsing
• Experience designing traceability or knowledge graph structures linking requirements, code, and documentation
• Prior exposure to software development workflows and Agile/DevOps environments
• Clean, modular coding style; comfortable with CI/CD and version control practices
• Excellent written and verbal communication skills (Upper-intermediate+ English)
  
   

Preferred Experience:

• Background in LLM application design for copilots or internal productivity assistants
• Understanding of enterprise software architecture, SDLC principles, and traceability compliance
• Familiarity with metadata-driven search, domain-specific chunking, and AI scalability challenges
• Exposure to knowledge graphs, internal developer portals, or enterprise RAG applications