GenAI Engineer - Banking (m/f/d)

Halian; Abu Dhabi; On-site; AED 350,000 - 550,000; Full time

Job summary

Halian is seeking a GenAI Engineer to design, develop, and deploy enterprise-grade Generative AI solutions with a focus on Conversational AI, RAG, and Agentic AI architectures. You will build AI-powered experiences leveraging LLMs, knowledge retrieval, and multi-agent orchestration to solve complex business challenges.

You will collaborate with stakeholders, architects, data and engineering teams to deliver scalable, secure, and production-ready AI systems, applying best practices in governance,

Qualifications

• Strong understanding of AI/ML fundamentals and Generative AI concepts.
• Hands-on experience designing and implementing RAG architectures.
• Experience with embeddings, vector databases, semantic search, and hybrid search.
• Proven ability to design Agentic AI solutions including multi-agent systems and A2A communication.
• Proficiency in Python and GenAI frameworks (LangChain, LangGraph, Semantic Kernel, CrewAI).
• Knowledge of REST APIs, cloud-native architectures, and AI deployment best practices.

Responsibilities

• Design, develop, and deploy enterprise-grade Generative AI and Conversational AI solutions.
• Build and optimize RAG architectures to improve response accuracy and grounding.
• Develop data ingestion pipelines for knowledge retrieval systems.
• Design vector search solutions using embeddings and vector databases.
• Create intelligent conversational experiences, chatbots, copilots, and virtual assistants.
• Design Agentic AI architectures and multi-agent orchestration frameworks.
• Implement agent governance, registries, and lifecycle management.

Skills

GenAI fundamentals

Conversational AI

RAG architectures

Agentic AI

Python

LangChain

LangGraph

Semantic Kernel

REST APIs

AI governance

Tools

LangChain

LangGraph

Semantic Kernel

CrewAI

Job description

GenAI Engineer (Conversational AI, RAG & Agentic AI)

Role Overview

We are seeking a highly skilled GenAI Engineer to design, develop, and deploy enterprise-grade Generative AI solutions, with a strong focus on Conversational AI, Retrieval-Augmented Generation (RAG), and Agentic AI architectures.

This role will be responsible for building intelligent AI-powered experiences that leverage large language models, knowledge retrieval systems, and multi-agent orchestration frameworks to solve complex business challenges. The successful candidate will work closely with business stakeholders, architects, data teams, and engineering teams to build scalable, secure, and production-ready AI solutions.

The ideal candidate will possess strong AI/ML fundamentals, hands-on experience with modern GenAI frameworks, and expertise in designing agent-based systems capable of reasoning, collaboration, and task execution.

Key Responsibilities

• Design, develop, and deploy enterprise-grade Generative AI and Conversational AI solutions
• Build and optimize RAG (Retrieval-Augmented Generation) architectures to enhance AI response accuracy and grounding
• Develop and manage document and data ingestion pipelines for knowledge retrieval systems
• Design and implement vector search solutions using embeddings and vector databases
• Develop intelligent conversational experiences, chatbots, copilots, and virtual assistants
• Design and implement Agentic AI architectures, including autonomous and collaborative agent workflows
• Build and manage orchestrator-based multi-agent systems for complex task execution and decision-making
• Implement agent governance mechanisms, including agent registries and agent lifecycle management
• Develop and support Agent-to-Agent (A2A) communication protocols and agent collaboration frameworks
• Define customer journeys, user goals, intent classification, and routing strategies for conversational systems
• Collaborate with product, business, and engineering teams to translate requirements into AI-driven solutions
• Ensure AI solutions meet enterprise standards for scalability, reliability, security, and governance
• Contribute to AI model evaluation, prompt engineering, testing, and continuous improvement initiatives

Required Skills & Qualifications

• Strong understanding of AI/ML fundamentals and Generative AI concepts
• Hands-on experience designing and implementing RAG architectures
• Experience working with:
  • Embeddings
  • Vector Databases
  • Semantic Search
  • Hybrid Search Architectures
• Experience building and managing document and data ingestion pipelines
• Strong expertise in Conversational AI development
• Proven experience designing and implementing Agentic AI solutions
• Experience with:
  • Multi-Agent Systems
  • Agent Orchestration Frameworks
  • Agent Registries
  • A2A (Agent-to-Agent) Communication Protocols
• Strong understanding of user journey mapping, goal-oriented workflows, and intent routing strategies
• Experience with Python and GenAI frameworks such as LangChain, LangGraph, Semantic Kernel, CrewAI, or equivalent
• Knowledge of REST APIs, cloud-native architectures, and AI deployment best practices
• Strong analytical, problem-solving, and stakeholder management skills

Preferred Skills & Experience

• Experience working with Azure OpenAI, AWS Bedrock, OpenAI, Anthropic Claude, or Google Gemini
• Knowledge of AI governance, guardrails, evaluation frameworks, and Human-in-the-Loop (HITL) patterns
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, ChromaDB, or Azure AI Search
• Exposure to MCP (Model Context Protocol) and advanced agent tooling frameworks
• Experience deploying AI solutions within enterprise or regulated environments
• Understanding of MLOps, LLMOps, CI/CD, and observability frameworks
• Experience in banking, financial services, or large-scale digital transformation programmes is preferred