Qualifications & Core Skills (Must-Have):-4+ years of overall experience in Data Science, Data Engineering, AI/ML Engineering, or related areas.5+ years of engineering experience in data/AI engineering or related technical domains.2+ years of hands-on experience with Vector Search / RAG / GenAI / LLM solutions.Strong hands-on experience in Python, SQL.Hands-on experience with Azure and Azure AI services.Strong understanding of Vector Databases, Vector Search, ANN indexing, similarity metrics, and retrieval optimization.Strong understanding of embedding models, embedding selection/evaluation, chunking strategies, embedding refresh, and drift handling.Hands-on experience with RAG architecture, including retrieval, context assembly, grounding, and source traceability.Experience building and optimizing vector indexes using technologies such as Azure AI Search, FAISS, pgvector, Pinecone, Milvus, or Microsoft Fabric Vector capabilities.Experience with Python-based data pipelines, APIs, and workflow orchestration.Ability to collaborate with Data Scientists, Data Engineers, GraphDB Engineers, AI/ML teams, and business stakeholders.Strong analytical, problem-solving, communication, and stakeholder management skills.Desirable Skills (Good-to-Have):-Direct hands-on experience with GraphRAG and graph + vector combined retrieval.Knowledge of Microsoft Fabric, OneLake, and Azure AI services.Familiarity with Microsoft Fabric NL2GQL / Data Agent capabilities.Experience with PySpark and API development.Experience optimizing LLM inference cost, latency, scalability, and performance.Experience with Azure AI Search, FAISS, pgvector, Pinecone, Milvus, or Fabric Vector Search.Key Responsibilities:-Design, build, and optimize production-grade Vector Search and RAG pipelines.Build RAG / GraphRAG solutions combining vector and graph-based retrieval.Implement ANN indexing, similarity search, and retrieval optimization.Work with Azure OpenAI / LLMs and develop retrieval-optimized prompts.Develop Natural Language-to-Query (NL2Query) solutions where applicable.Build retrieval evaluation frameworks and continuously improve accuracy, relevance, latency, and grounding.Apply Now:-Interested candidates can share their resume at: riyaraj@huquo.comCC: career@huquo.com
3 days ago