AI Engineer (Agentic AI, LLM & RAG)

Quick Facts

• Role: AI Engineer (Agentic AI, LLM & RAG)

Description

You will build and develop an Agentic AI platform used to support bank business processes. Responsibilities include designing multi-agent architectures, integrating LLM-based solutions with enterprise systems, developing ML components, and implementing RAG along with evaluation and monitoring to support automation and digitization.

Responsibilities

• Design, develop, and maintain Agentic AI solutions for business processes

• Build, develop, and maintain systems based on Large Language Models (LLM)

• Design and implement RAG (Retrieval Augmented Generation) solutions

• Build multi-agent architectures using frameworks such as Agno and LangGraph (or equivalent solutions)

• Integrate AI agents with bank business systems via APIs and integration services

• Develop and maintain AI components in Python

• Develop and maintain Machine Learning components supporting Agentic AI

• Create evaluation, monitoring, and observability mechanisms for AI solutions

• Optimize answer quality, reduce hallucinations, and develop AI safety and control mechanisms

• Collaborate with business teams, architects, IT teams, and security teams during AI deployment

Requirements

• Minimum 5 years of commercial Python programming experience

• Practical experience designing and implementing LLM-based solutions

• Practical experience building RAG solutions

• Experience designing and implementing Agentic AI solutions

• Knowledge of frameworks such as Agno, LangGraph, LangChain, LlamaIndex (or equivalents)

• Experience integrating AI solutions with business systems via APIs

• Knowledge of ML/AI libraries and frameworks, especially PyTorch, TensorFlow, and Hugging Face

• Practical knowledge of vector databases (Qdrant, ChromaDB, Weaviate, Milvus, or equivalents)

• Knowledge of embeddings, reranking, and response quality optimization

• Experience building backend services using FastAPI

• Knowledge of AI observability and evaluation topics (e.g., Langfuse, LangSmith, Promptfoo, DeepEval)

• Knowledge of Docker and Kubernetes/OpenShift

• Knowledge of MLOps and LLMOps

• Ability to design AI solution architecture for enterprise environments

• Ability to work with business and technical teams