Enterprise Agentic RAG Platform
Agentic RAG over 17K+ enterprise documents with multi-agent orchestration on Azure.
17K+ documents · 90% faster responses
RAGLangChainAzure OpenAI
View Case Study Production AI Systems
I build AI systems that hold up in production.
I'm Sravan Kumar Yadav, an AI/ML engineer. I build systems that work in production for real users, with clear thinking, solid engineering, and results that matter. Outside day-to-day delivery, I write about what I learn while building and evaluating these systems.
17K+
Enterprise Documents Processed
90%
Faster RAG Response Time
80%
Less Manual Deck Effort
The Story
About
A little of the person behind the work.
I got into AI because it felt alive. The field was moving, and I did not want to watch from the outside. I wanted to build inside it.
That same energy shows up in how I work. I get curious, dig in, and I stay with a problem until it makes sense. What is broken, why it broke, what we can do next. Simple questions. They keep me honest.
When something finally clicks, I like to write it down. Outside work, I run, stay serious about fitness, and I travel when I can. More than anything, I want people to feel steady around my name: that I can be trusted, and that I know what I am doing.
The Journey
Experience
Enterprise AI work measured by outcomes, not tooling.
Jul 2024 – Present
AI/ML Engineer
Accellor Software Pvt. Ltd. · Hyderabad
Build and ship AI systems for enterprise clients — helping teams find answers faster, automate heavy document work, and keep outputs grounded and reviewable.
- Shipped an enterprise AI search and Q&A platform across 17K+ business documents, so teams can find reliable answers without digging through files by hand
- Cut AI response time by over 90% through better retrieval design and caching — faster answers for users, lower wait cost for the business
- Automated RFP-to-proposal drafting with multi-agent AI, turning long document review into structured first drafts instead of blank-page effort
- Added human review for uncertain cases, so experts stay in control where the AI should not decide alone
- Delivered these systems on Azure for production use — secure, reliable, and ready for real client workloads
The Toolkit
Skills
What I reach for in production AI systems.
Core practice
AI & Automation
How I design and ship agent systems.
RAGMulti-Agentic RAGLLMsSLMsLangChainLangGraphLangSmithLangFuseAgnoCrew AIPrompt EngineeringSemantic SearchHybrid SearchHugging Face
The Work
Projects
Systems I am proud to have built.
Multi-Agentic RFP Proposal Platform
Multi-agent RFP-to-proposal drafts with HITL review and Service Bus jobs.
Faster proposal turnaround
Multi-AgentFastAPIAzure
View Case Study 
Document Ingestion & Embedding Pipeline
Automated ingestion from SharePoint, ADI, and Blob Storage with Container App Jobs for embedding generation and delta/retry processing.
Delta + retry resilient jobs
AzureDataEmbeddings
View Case Study Credentials
Certifications
Verified credentials that back the work.
The Thinking
Blogs
Notes on building applied AI.
Aug 23, 2026 · 5 min read
How Do You Evaluate a RAG App? (Part 2: The Generation Report Card)
Agentic AiRetrieval EvaluationRagsLlm Evaluation
Part 1 convinced the interviewer that retrieval could be flawless and this is when he start showing up the rea
Read on Medium
Aug 20, 2026 · 7 min read
How Do You Evaluate a RAG App? (Part 1: The Retrieval Report Card)
Llm EvaluationRetrieval EvaluationRagsGenai
Someone in an interview leans forward and asks: “How do you evaluate your RAG / LLM application?” I used to sa
Read on MediumGet In Touch
Contact
Building something interesting? Let us talk.
Open to AI/ML roles and freelance projects that are a good fit. I usually reply within a day.