Experience:

• 4-7 years in software/AI engineering
• At least 2 years of hands-on LLM or Generative AI development
• Prior experience delivering AI solutions in an IT services or consulting environment is a plus

Responsibilities:

• Architect and deliver production-grade Generative AI solutions for enterprise clients
• Design and deploy end-to-end LLM-powered pipelines for document intelligence, information extraction, and semantic search
• Build multi-agent systems and agentic workflows with tool use, memory, planning, and multi-step reasoning
• Architect and maintain RAG systems with retrieval, chunking, re-ranking, and evaluation strategies
• Integrate enterprise and cloud LLM APIs with custom wrappers, structured output parsing, and error handling
• Develop and expose AI capabilities as REST APIs using FastAPI
• Containerise and deploy AI services on AKS
• Implement CI/CD pipelines via Azure DevOps for scalable AI service delivery
• Evaluate model and agent performance using RAGAS, DeepEval, and LLM-as-judge
• Engage with client stakeholders to translate business requirements into AI solution architectures
• Mentor junior engineers and contribute to team capability building
• Work across the full stack from agentic AI systems and LLM pipelines to RAG architectures and cloud deployment on Azure

Nice to have:

• Knowledge of RAG evaluation frameworks such as RAGAS and DeepEval
• Exposure to unstructured data processing such as emails, PDFs, and invoices
• Familiarity with MCP (Model Context Protocol) or OpenAI Assistants API for tool-augmented agents
• Experience with AI observability and tracing tools

More skills:

OOP, async, agentic AI systems, tool calling, agent orchestration, memory, multi-agent collaboration, Azure AI services, Azure Document Intelligence, AKS, Azure DevOps, embedding models, Docker, Kubernetes, CI/CD, DeepEval, LLM-as-judge

Other:

• Full-Time
• GBS practice
• Reference Number: PEPPGS01-101-1