RAG + Agentic AI Lead

RAG + Agentic AI Lead About Us At Codvo, we are committed to building scalable, future-ready data platforms that power business impact. We believe in a culture of innovation, collaboration, and growth, where engineers can experiment, learn, and thrive. Join us to be part of a team that solves complex data challenges with creativity and cutting-edge technology. About the Role We are looking for a highly skilled RAG + LLM-based Agentic AI Engineer to build production-grade retrieval systems, multi-agent workflows, and enterprise-ready AI applications. You will work across document pipelines, model orchestration, tool-driven agents, and governed AI systems that power Codvo’s next-generation products . Key Responsibilities - Build end-to-end RAG pipelines: smart chunking, hybrid retrieval, reranking, query rewriting. - Implement LangGraph-based agentic workflows with tools, planning, and self-healing behaviors. - Develop and optimize vector search systems (Qdrant/Weaviate/OpenSearch). - Design multi-tenant, ontology-driven knowledge layers for enterprise data. - Implement guardrails, hallucination reduction, and automated evals. - Build and maintain document ingestion pipelines (PDF, DOCX, OCR, images). - Architect and deploy FastAPI-based AI microservices with caching and async execution. - Integrate LLM systems with enterprise apps (SharePoint, CRM, databases, MCP tools). - Ensure security, PII safety, auditability, and governance requirements are met. - Collaborate with solution architects and domain SMEs to translate use cases into working AI systems. Lead and mentor a team of AI/ML engineers, providing technical guidance, architectural direction, and code reviews. Core Skills & Competencies RAG Engineering: - Smart/component-aware chunking - Hybrid retrieval (BM25 + dense) - Reranking - Graph-RAG basics - Query rewriting & multi-hop retrieval Agentic AI: - LangGraph - MCP tools - Multi-agent orchestration - Tool-calling workflows Vector & Search: - Qdrant or Weaviate - OpenSearch/Elasticsearch - HNSW tuning LLM Ops: - Prompt engineering - Hallucination control - RAG/agent eval frameworks - Synthetic data generation Backend & Infra: - Python, FastAPI - Async programming - Docker, CI/CD - Cloud basics Data Engineering: - Document parsing - ETL pipelines - Caching, batching, streaming Security & Governance: - PII handling - Access control - Audit trails Nice-to-Have - Experience with Haystack, LlamaIndex, or RAG frameworks - Fine-tuning retrievers or small LLMs - Ontology modeling - Enterprise search deployments - Agents in customer support, ops, legal, engineering What You’ll Get - Work on cutting-edge agentic AI systems at production scale - Ownership over enterprise-grade architectures - Fast growth environment - Influence Codvo’s platform and accelerators Experience: 7+ Years