Senior AI Engineer
Summary
Senior AI Engineer taking end-to-end ownership of production AI agents for a global consulting firm's in-house tech consultancy: building RAG pipelines, Teams-deployed conversational agents, and LLM data-quality workflows on Azure (OpenAI, AI Search, Functions, Foundry). Remote possible, on-site preferred in Prague; B2B contract.
🚀 Senior AI Engineer | Azure OpenAI, RAG & AI Agents | Enterprise GenAI Solutions 🌍 Remote | 📄 B2B Contract |
We are looking for a hands-on Senior AI Engineer to join our client, an in-house technology consultancy of a global consulting firm, delivering production-grade AI agents and modern GenAI architectures for enterprise ecosystems. In this role, you will take end-to-end technical ownership of building connected AI solutions - ranging from dynamic RAG-powered assistants to automated LLM data-quality pipelines - while turning architectural patterns into reusable agent templates for future enterprise scale.
What You’ll Be Doing:
- Designing, orchestrating, and deploying production AI agents on Microsoft Foundry, owning end-to-end prompt design and execution logic.
- Architecting robust RAG pipelines with Azure AI Search and Blob Storage, covering ingestion, chunking, indexing, and verifiable source retrieval.
- Publishing conversational agents to Microsoft Teams using Azure Bot Service, incorporating human-in-the-loop workflows and escalation paths.
- Building automated LLM workflows to evaluate data quality and remediate records deterministically without hallucinations.
- Developing event-driven integration microservices on Azure Functions and Container Apps with secure write-backs to enterprise target systems.
- Establishing comprehensive observability, tracing, and latency monitoring using Azure Monitor and Application Insights.
- Packaging components into modular, reusable agent templates and authoring clear architectural documentation.
What We’re Looking For:
- 5+ years of software engineering experience, including 2+ years shipping production-grade LLM or GenAI solutions.
- Strong software engineering foundation in Python (TypeScript is a plus).
- Deep hands-on experience across Azure OpenAI, Microsoft Foundry, Azure AI Search, and modern RAG architectures.
- Practical experience with serverless cloud patterns: Azure Functions, Container Apps, REST APIs, and webhooks.
- Solid understanding of enterprise cloud security: Entra ID, Key Vault, managed identities, and secure networking.
- Expertise in systematic LLM evaluation methods (rubric scoring, regression test sets, LLM-as-a-judge).
- Consultant mindset: ability to guide technical decisions, bridge business workflows into scalable architectures, and collaborate smoothly across global stakeholders.
Must-Haves:
- 5+ years in software engineering with 2+ years of production GenAI/LLM delivery.
- Proven expertise in Python, Azure OpenAI / Microsoft Foundry, Azure AI Search, and RAG architectures.
- Hands-on experience with Azure Functions or Container Apps, REST APIs, and webhooks.
- Working knowledge of Entra ID, Key Vault, and basic Azure networking.
- Fluency in both Czech and English for daily technical collaboration.
Location & Working Setup:
- Remote working model possible, preffered on-stie in Prague .
- US Hours overlap needed: Minimum 2:00 PM – 6:00 PM CET (preferred 2:00 PM – 7:00 PM CET).
Ready to build and scale mission-critical AI agents at enterprise level? Apply directly or reach out with your CV to discuss the role in detail!
Skills
Sign in to read and join the discussion.