Senior GenAI Engineer (LLM Applications on Azure)

Luxoft; Polska; On-site; PLN 180,000 - 240,000; Full time

Job summary

Luxoft seeks an expert GenAI engineer to design and implement LLM applications and agent workflows on Azure OpenAI, including RAG pipelines, embeddings, and multi-agent orchestration. You will drive evaluation, guardrails, and cost control while mentoring peers in GenAI patterns.

Ideal candidates bring 10+ years in software/data engineering with 3+ years in ML/NLP and proven production LLM delivery, plus strong Python and modern tooling expertise.

Qualifications

• Bachelor's degree in Computer Science, Engineering, Information Systems or related field.
• 10+ years in software or data engineering, with 3+ in ML/NLP and 2+ delivering production LLM apps on Azure OpenAI or equivalent.
• Expert Python; LangGraph, LangChain and/or Semantic Kernel; asynchronous, event-driven design.
• MCP server/client development, function calling, multi-agent orchestration and state management.
• LLM evaluation, fine-tuning with LoRA/PEFT and model selection.
• Guardrails, LLM observability and FinOps for inference.

Responsibilities

• Build LLM applications and agent workflows on Azure OpenAI; design RAG pipelines.
• Integrate enterprise tools via MCP servers and multi-agent orchestration.
• Engineer, test prompts; perform offline/online evaluations and fine-tuning where justified.
• Implement guardrails and observability; optimise token/inference costs; report against budgets.
• Document prompts, evaluation results and model choices; mentor engineers adopting GenAI patterns.

Job description

Private Medical & Dental care & Life Insurance covered

Internal Mobility program - possibility of rotation between projects, locations, accounts

...and more!

Project Description:

Expert-level engineer designing and building LLM applications and agentic workflows on Azure: RAG pipelines, multi-agent orchestration, MCP tool integration, evaluation, guardrails and cost control. Sets the GenAI engineering standards for the account and is accountable for solution quality against agreed evaluation thresholds.

Responsibilities:

• Build LLM applications and agent workflows with LangGraph / LangChain / Semantic Kernel on Azure OpenAI (AWS Bedrock / GCP Vertex a plus).
• Design RAG pipelines: document ingestion, chunking strategies, embeddings, vector search (Azure AI Search, FAISS, Pinecone), hybrid retrieval and re-ranking.
• Integrate enterprise tools and context via Model Context Protocol (MCP) servers and function / tool calling; design multi-agent systems.
• Engineer, version and test prompts; run offline and online evaluations (accuracy, grounding, hallucination rate) and fine-tuning where justified.
• Implement responsible-AI guardrails (content filters, PII redaction, policy checks) and LLM observability (tracing, token accounting, latency).
• Optimise token and inference cost (model routing, caching, batching); report against cost budgets.
• Document prompts, evaluation results and model choices; mentor engineers adopting GenAI patterns.

Mandatory Skills Description:

• Bachelor's degree in Computer Science, Engineering, Information Systems or a related field, or equivalent practical experience.
• 10+ years in software or data engineering, of which 3+ in machine learning / NLP and 2+ delivering production LLM applications (RAG, agents) on Azure OpenAI or equivalent.
• Expert Python; LangGraph, LangChain and/or Semantic Kernel; asynchronous, event-driven application design.
• MCP server / client development, function calling, multi-agent orchestration and state management.
• LLM evaluation (RAGAS, promptfoo, Azure AI evaluation or equivalent), fine-tuning (LoRA / PEFT) and model selection.
• Guardrails (Azure AI Content Safety, NeMo Guardrails or similar), LLM observability (LangSmith, OpenTelemetry), FinOps for inference.

Nice-to-Have Skills Description:

• AWS Bedrock or GCP Vertex AI.
• Experience in financial services, sovereign wealth / investment holding or other regulated enterprise environments.
• Experience working with distributed teams (onsite UAE with nearshore India / offshore Poland squads).