Question
FULL_TIME
Remote
5-10

RAG + Agentic AI Engineer (India) (Remote)

11/21/2025

The role involves building production-grade retrieval systems and multi-agent workflows. You will also work on document pipelines and model orchestration to enhance Codvo’s AI applications.

Working Hours

40 hours/week

Company Size

51-200 employees

Language

English

Visa Sponsorship

No

About The Company
At Codvo.ai, we help enterprises move beyond AI experimentation to real AI execution. We design, train, and operate AI systems that integrate seamlessly into enterprise workflows—delivering reliable, governed, and measurable outcomes. Powered by Hybrid Teams and our NeIO 2.0 Operational AI Platform, we enable organizations to scale AI from pilots to production—transforming operations with intelligent automation, digital coworkers, and continuous optimization. Codvo.ai — Enterprise AI Execution
About the Role
<div><br></div><p style="margin-bottom:0cm;"><strong>Job Description — RAG + Agentic AI Engineer</strong></p><div><br></div><p style="margin-bottom:0cm;"><strong>About Us</strong></p><p style="margin-bottom:0cm;">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.</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;"><strong>About the Role</strong></p><p style="margin-bottom:0cm;">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</p><p style="margin-bottom:0cm;">.</p><p style="margin-bottom:0cm;"><strong>Key Responsibilities</strong></p><p style="margin-bottom:0cm;">- Build end-to-end RAG pipelines: smart chunking, hybrid retrieval, reranking, query rewriting.</p><p style="margin-bottom:0cm;">- Implement LangGraph-based agentic workflows with tools, planning, and self-healing behaviors.</p><p style="margin-bottom:0cm;">- Develop and optimize vector search systems (Qdrant/Weaviate/OpenSearch).</p><p style="margin-bottom:0cm;">- Design multi-tenant, ontology-driven knowledge layers for enterprise data.</p><p style="margin-bottom:0cm;">- Implement guardrails, hallucination reduction, and automated evals.</p><p style="margin-bottom:0cm;">- Build and maintain document ingestion pipelines (PDF, DOCX, OCR, images).</p><p style="margin-bottom:0cm;">- Architect and deploy FastAPI-based AI microservices with caching and async execution.</p><p style="margin-bottom:0cm;">- Integrate LLM systems with enterprise apps (SharePoint, CRM, databases, MCP tools).</p><p style="margin-bottom:0cm;">- Ensure security, PII safety, auditability, and governance requirements are met.</p><p style="margin-bottom:0cm;">- Collaborate with solution architects and domain SMEs to translate use cases into working AI systems.</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;"><strong>Core Skills &amp; Competencies</strong></p><p style="margin-bottom:0cm;">RAG Engineering:</p><p style="margin-bottom:0cm;">- Smart/component-aware chunking</p><p style="margin-bottom:0cm;">- Hybrid retrieval (BM25 + dense)</p><p style="margin-bottom:0cm;">- Reranking</p><p style="margin-bottom:0cm;">- Graph-RAG basics</p><p style="margin-bottom:0cm;">- Query rewriting &amp; multi-hop retrieval</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;">Agentic AI:</p><p style="margin-bottom:0cm;">- LangGraph</p><p style="margin-bottom:0cm;">- MCP tools</p><p style="margin-bottom:0cm;">- Multi-agent orchestration</p><p style="margin-bottom:0cm;">- Tool-calling workflows</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;">Vector &amp; Search:</p><p style="margin-bottom:0cm;">- Qdrant or Weaviate</p><p style="margin-bottom:0cm;">- OpenSearch/Elasticsearch</p><p style="margin-bottom:0cm;">- HNSW tuning</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;">LLM Ops:</p><p style="margin-bottom:0cm;">- Prompt engineering</p><p style="margin-bottom:0cm;">- Hallucination control</p><p style="margin-bottom:0cm;">- RAG/agent eval frameworks</p><p style="margin-bottom:0cm;">- Synthetic data generation</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;">Backend &amp; Infra:</p><p style="margin-bottom:0cm;">- Python, FastAPI</p><p style="margin-bottom:0cm;">- Async programming</p><p style="margin-bottom:0cm;">- Docker, CI/CD</p><p style="margin-bottom:0cm;">- Cloud basics</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;">Data Engineering:</p><p style="margin-bottom:0cm;">- Document parsing</p><p style="margin-bottom:0cm;">- ETL pipelines</p><p style="margin-bottom:0cm;">- Caching, batching, streaming</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;">Security &amp; Governance:</p><p style="margin-bottom:0cm;">- PII handling</p><p style="margin-bottom:0cm;">- Access control</p><p style="margin-bottom:0cm;">- Audit trails</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;"><strong>Nice-to-Have</strong></p><p style="margin-bottom:0cm;">- Experience with Haystack, LlamaIndex, or RAG frameworks</p><p style="margin-bottom:0cm;">- Fine-tuning retrievers or small LLMs</p><p style="margin-bottom:0cm;">- Ontology modeling</p><p style="margin-bottom:0cm;">- Enterprise search deployments</p><p style="margin-bottom:0cm;">- Agents in customer support, ops, legal, engineering</p><p style="margin-bottom:0cm;"><br></p><p style="margin-bottom:0cm;"><strong>What You’ll Get</strong></p><p style="margin-bottom:0cm;">- Work on cutting-edge agentic AI systems at production scale</p><p style="margin-bottom:0cm;">- Ownership over enterprise-grade architectures</p><p style="margin-bottom:0cm;">- Fast growth environment</p><p style="margin-bottom:0cm;">- Influence Codvo’s platform and accelerators</p><div><br></div><div>Experience: 5+ Years</div>
Key Skills
RAG EngineeringAgentic AIVector & SearchLLM OpsBackend & InfraData EngineeringSecurity & Governance
Categories
TechnologyData & AnalyticsSoftwareEngineering
Apply Now

Please let Codvo.ai know you found this job on InterviewPal. This helps us grow!

Apply Now
Prepare for Your Interview

We scan and aggregate real interview questions reported by candidates across thousands of companies. This role already has a tailored question set waiting for you.

Elevate your application

Generate a resume, cover letter, or prepare with our AI mock interviewer tailored to this job's requirements.