AI Engineer - Azure

Join to apply for the AI Engineer - Azure role at VDart
.

We are seeking a forward-thinking AI Engineer to architect and deploy intelligent systems powered by Large Language Models (LLMs), Retrieval Augmented Generation (RAG), and advanced chunking strategies. This role is ideal for engineers passionate about building scalable production‑grade AI applications that leverage cutting‑edge retrieval and generation techniques.

• Design and implement RAG pipelines using hybrid search, vector keyword, semantic ranking, and metadata enrichment.
• Apply chunking strategies (fixed size, recursive, semantic, agentic) to optimize document segmentation for retrieval and embedding.
• Fine‑tune and evaluate LLMs (e.g., GPT, LLaMA, Ollama) for tasks such as QA, summarization, NER, and sentiment analysis.
• Build multi‑agentic systems.
• Integrate AI capabilities into enterprise applications using Azure OpenAI, Cognitive Search, Azure Functions, and Power Automate.
• Collaborate with stakeholders to translate business needs into scalable AI solutions.
• Ensure model reliability, performance, and ethical compliance across deployments.

• 8 to 12 years of experience as a Full‑Stack developer with at least 2 to 4 years in generative AI or RAG systems.
• Experience with chunking techniques and embedding strategies.
• Proficiency with MLOps tools (MLflow, Docker, CI/CD pipelines).
• Experience in prompt engineering and model evaluation.
• Mandatory familiarity with Agentic Systems and Multi‑Agent Orchestration.
• Python expertise.
• Strong knowledge of AI solutions.
• Professional experience with Azure Cognitive Services.
• Understanding of SDLC lifecycle.
• Excellent partner and client communication skills.

Not Applicable

Contract

Information Technology

Referrals increase your chances of interviewing at VDart by 2×.