Senior AI Engineer - Agentic AI

EPAM Systems; United Arab Emirates; Hybrid; AED 300,000 - 540,000; Full time

Job summary

EPAM Systems in the UAE seeks a Senior AI Engineer for Agentic AI to design and build scalable platforms integrating LLMs, multi-agent orchestration, and RAG for enterprise solutions.

You will develop orchestration engines, evaluation tooling, and governance to ensure secure, scalable AI workflows across Dubai or Abu Dhabi offices in a hybrid setup.

Qualifications

• Bachelor's or Master's degree in Computer Science or related field (PhD is a plus).
• Practical experience delivering Generative AI or Agentic AI systems into production.

Responsibilities

• Design and deploy Generative AI and Agentic AI solutions from prototype to production.
• Implement multi-agent orchestration patterns using various frameworks.
• Develop orchestration backbones for complex workflows including planning and retries.
• Build and optimize RAG pipelines with embeddings and vector DBs.
• Create memory/context management solutions and robust Python APIs (FastAPI).
• Ensure enterprise security and governance (RBAC, safety checks).
• Contribute to architectural decisions and engineering standards.

Skills

Python

API design

LLMs

Agent orchestration

RAG

FastAPI

CI/CD

Azure OpenAI

LangGraph

Security & governance

Education

Bachelor/Master in CS

PhD a plus

Tools

Docker

Kubernetes

Pinecone

Weaviate

Qdrant

OpenTelemetry

MLflow

Airflow

Langfuse

Semantic Kernel

Job description

We're looking for a Senior AI Engineer - Agentic AI to join our team in UAE out of either our Dubai or Abu Dhabi offices in a hybrid working mode. In this role, you will design and build scalable agentic AI platforms that integrate Large Language Models (LLMs), multi-agent orchestration and retrieval-augmented generation (RAG) patterns into production-ready enterprise solutions. You will focus on creating reusable platform components, orchestration engines and governance frameworks that allow complex AI workflows to operate securely and efficiently at scale. You will be responsible for developing advanced orchestration capabilities, implementing evaluation and observability tooling and embedding enterprise controls for compliance and safety. If you are passionate about innovating with AI in real-world applications and scaling intelligent systems, this role offers an opportunity to make a significant impact in production-grade AI engineering.

Responsibilities

• Design, build and deploy Generative AI and Agentic AI solutions from prototype to production
• Implement multi-agent orchestration patterns using frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel or OpenAI Agents SDK
• Develop the orchestration backbone for advanced workflows including planning, checkpointing, retries, fallback handling and resumption of long-running processes
• Build and optimize RAG pipelines, including chunking strategies, embeddings, vector/hybrid search and retrieval evaluation with grounded responses and citations
• Develop memory and context management solutions, including short-term and long-term stores and compaction strategies
• Write robust Python APIs and services (e.g., FastAPI), incorporating async execution, background jobs and containerized deployments
• Integrate enterprise systems and tools using protocols such as MCP, A2A, OpenAPI, REST and gRPC, ensuring graceful degradation and retries
• Apply enterprise security and governance practices including RBAC, prompt safety checks, traceability and secrets management
• Implement evaluation pipelines and observability frameworks using tools such as Langfuse, Arize or OpenTelemetry
• Contribute to architectural design decisions, code reviews and engineering standards for platform development

Requirements

• Bachelor's or Master's degree in Computer Science, Engineering or related field (PhD is a plus)
• Practical experience delivering Generative AI or Agentic AI systems into production environments
• Expertise in Python engineering for APIs, microservices, testing and CI/CD workflows
• Strong working knowledge of LLM capabilities, including prompt design, structured outputs, tool calling and retrieval strategies
• Hands-on experience with agent orchestration frameworks (LangGraph, AutoGen, CrewAI or Semantic Kernel)
• Proven experience with RAG implementations, embeddings and vector database integrations
• Familiarity with stateful or long-running systems, including checkpointing and resumable workflows
• Cloud deployment experience (Azure preferred), using services such as Azure OpenAI, AI Foundry or AI Search, with Docker and Kubernetes
• Understanding of schema validation frameworks (e.g., JSON Schema, Pydantic) and MLOps tools such as MLflow or Airflow
• Strong communication ability to explain trade-offs around cost, latency and accuracy to technical and non-technical audiences

Nice to have

• Experience using Azure AI Foundry or Microsoft Agent Framework
• Knowledge of MCP and A2A protocols for agent and tool interoperability
• Hands-on work with vector databases like Pinecone, Weaviate, Qdrant or pgvector
• Familiarity with distributed systems, workflow engines (Temporal, Airflow or Dagster) and event-driven architectures
• Experience with open-source LLMs or Small Language Models for custom deployments
• Knowledge of AI safety and governance: guardrails, output filtering and red-teaming practices
• Background in fine-tuning or adapting foundation models (e.g., LoRA, distillation) for domain-specific tasks