Azure GenAI Engineer: LLM Apps & Multi-Agent Systems

Luxoft; Abu Dhabi; On-site; AED 350,000 - 700,000; Full time

Job summary

Luxoft is seeking an expert-level engineer to design and build LLM applications and agent workflows on Azure OpenAI, setting GenAI engineering standards for the account. The role focuses on RAG pipelines, multi-agent orchestration, MCP tool integration, evaluation, guardrails and cost control, with accountability for solution quality against defined evaluation thresholds.

Strong Python, LangGraph/LangChain/Semantic Kernel expertise is required, with mentoring responsibilities and collaboration

Qualifications

• Bachelor's degree or equivalent practical experience in CS/Engineering/IS.
• 10+ years in software or data engineering with 3+ years in ML/NLP.
• 2+ years delivering production LLM applications (RAG, agents) on Azure OpenAI or equivalent.
• Expert Python with LangGraph, LangChain and/or Semantic Kernel.
• Experience with prompt engineering, evaluation, and guardrails.

Responsibilities

• Build LLM applications and agent workflows on Azure OpenAI.
• Design RAG pipelines with document ingestion, embeddings, vector search, and hybrid retrieval.
• Integrate MCP servers and multi-agent orchestration.
• Engineer prompts and conduct offline/online evaluations and fine-tuning as needed.
• Implement guardrails and LLM observability and optimize costs.
• Document results and mentor engineers adopting GenAI patterns.

Skills

Python

LangGraph

LangChain

Semantic Kernel

Asynchronous programming

Distributed systems

LLM evaluation

Prompt engineering

Model cost optimization

NLP

Education

Bachelor's degree in CS/Engineering/IS

Equivalent practical experience

Tools

Azure OpenAI

FAISS

Pinecone

LangSmith

OpenTelemetry

MCP servers

NeMo Guardrails

LoRA/PEFT

Job description

Luxoft is seeking an expert-level engineer to design and build LLM applications and agent workflows on Azure OpenAI, setting GenAI engineering standards for the account. The role focuses on RAG pipelines, multi-agent orchestration, MCP tool integration, evaluation, guardrails and cost control, with accountability for solution quality against defined evaluation thresholds.

Strong Python, LangGraph/LangChain/Semantic Kernel expertise is required, with mentoring responsibilities and collaboration