Description

You will architect and deploy intelligent systems powered by Large Language Models (LLMs) and Retrieval Augmented Generation (RAG).

Responsibilities

• 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 QA, summarization, NER, and sentiment analysis.
• Build multi-agentic systems and integrate AI capabilities into enterprise applications using Azure OpenAI, Cognitive Search, Azure Functions, and Power Automate.
• Ensure model reliability, performance, and ethical compliance across all deployments.

Required Skills

• 8 to 12 years of experience as a Fullstack developer, with 2 to 4 years specifically in generative AI or RAG systems.
• Proficiency in Azure AI Studio and Azure Cognitive Services.
• Experience with Vector Databases (e.g., Pinecone, FAISS), chunking techniques, and embedding strategies.
• Familiarity with MLOps tools, specifically MLflow, Docker, and CI/CD pipelines.
• Expert proficiency in Python and React.
• Expert knowledge of AI Solutions and Azure Cognitive Solutions.
• Expertise in prompt engineering and model evaluation.
• Good knowledge of ADO/Azure DevOps.
• Familiarity with Agentic Systems and MultiAgent Orchestration.

Key Skills

Education

Any Graduate