Job Description

Identify, design and deliver AI initiatives for customers, with primary focus on Retrieval-Augmented Generation (RAG), enterprise AI applications, intelligent automation, GenAI-based solutions and Agentic AI frameworks.

KEY RESPONSIBILITIES

• Strong expertise in RAG architecture and implementation, including
  • Data ingestion pipelines
  • Document chunking strategies
  • Embeddings and semantic retrieval
  • Hybrid search and reranking
  • Evaluation metrics and hallucination mitigation
• Experience with vector databases such as Pinecone/FAISS/Weaviate
• Hands-on experience with LLM APIs (OpenAI, Anthropic, Azure OpenAI) and prompt orchestration.
• Proficiency in LangChain, LlamaIndex, or equivalent frameworks for conversational workflows and RAG applications.
• Experience integrating AI solutions with APIs, enterprise systems, and automation workflows.
• Exposure to multi-agent orchestration, tool-calling, and autonomous workflows preferred but not mandatory.
• Lead and mentor a team of 3–4 engineers delivering customer-facing AI initiatives.
• Drive discovery, solution design, and deployment of GenAI and RAG use cases.
• Own innovation roadmap for AI offerings within EIRS.
• Work with stakeholders to identify new opportunities for knowledge assistants, copilots, document intelligence, and AI automation.

EXPERIENCE, SKILLS & COMPETENCIES

• 6–10 year's total software engineering experience
• 3+ years implementing production-grade RAG or GenAI solutions
• Experience leading small engineering teams or workstreams preferred
• Strong RAG architect with hands-on engineering depth
• Experience translating customer problems into deployable GenAI solutions
• Experience building and working with agentic AI frameworks
• Track record improving search quality, latency, and AI response accuracy
• Comfortable leading teams and driving innovation initiatives