# Rithin Pallikonda > AI / Gen AI Engineer | RAG Pipelines · LangGraph Agents · Azure OpenAI · LLM Fine-Tuning Location: Dallas-Fort Worth Metroplex, United States Profile: https://flows.cv/rithin AI / Gen AI Engineer with 4+ years of engineering experience, including 2+ years specialising in production LLM applications at enterprise scale. I've shipped 9 production AI features across PayCom and DarwinBox — RAG chatbots, document intelligence pipelines, multi-turn conversational agents, anomaly explanation engines, and a LangGraph-based agentic audit system — all on the Microsoft Azure AI stack, serving Fortune 500 and enterprise clients. 🔧 What I build: • End-to-end RAG pipelines — Azure Databricks preprocessing → Azure AI Search (hybrid BM25 + dense retrieval, MMR re-ranking) → LangChain orchestration → AKS deployment • Agentic AI workflows — LangGraph multi-node state graphs with tool registries, conditional edges, and human-in-the-loop approval layers • Document intelligence — Azure Document Intelligence + OpenCV + GPT-4o function calling with Pydantic schema validation and Map-Reduce for multi-page contracts • LLM fine-tuning — LoRA/PEFT on Azure ML, improving payroll intent classification F1 from 0.72 → 0.91 • LLM evaluation — RAGAS pipelines (faithfulness, answer relevance, context precision) integrated into Azure DevOps CI/CD as quality gates 📊 Measurable outcomes: • 38% reduction in HR support ticket volume • 60% faster document processing time • 71% improvement in anomaly resolution rates • 84% self-resolution rate on employee self-service queries • 99.7% MongoDB storage reduction (150 GB → 500 MB) improving LLM retrieval latency 🛠 Core stack: Azure OpenAI · LangChain · LangGraph · Azure AI Search · Azure Databricks · AKS · FastAPI · Python · MongoDB · RAGAS · W&B 🎓 MS Computer Science — University of Texas at Arlington (GPA 3.6) Open to AI Engineer, Gen AI Engineer, and ML Engineer roles. Let's connect. ## Work Experience ### Gen AI Engineer @ Paycom Jan 2024 – Present | United States 🤖 HR Policy RAG Chatbot Conversational RAG chatbot using Azure OpenAI GPT-4o mini, LangChain, and Azure AI Search — ingesting 500+ policy documents via Azure Databricks (PySpark + spaCy), hybrid BM25 + dense retrieval, MMR re-ranking, and multi-turn memory. Reduced HR support ticket volume by 38%. Deployed on AKS with Azure DevOps CI/CD; RAGAS evaluation gate on every push; Azure Redis Cache cutting API costs by 40%. ⚡ Payroll Anomaly Explanation Engine LLM explanation layer on PayCom's rules-based anomaly detection system — enriching flags with 6-period payroll history and HR event context from Azure SQL + Cosmos DB, generating structured plain-English investigation summaries via GPT-4o JSON mode. Deployed as Azure Functions triggered by Azure Service Bus. Improved admin action rate on anomalies by 71%. 💬 Employee Self-Service AI Assistant Two-layer conversational assistant: Layer 1 fetches live personal payroll data from Azure SQL scoped to the authenticated employee; Layer 2 retrieves policy context from Azure AI Search. LangChain router classifies query type in real-time; Redis session memory for multi-turn context; WebSocket token streaming via React.js. Handles 2,000+ daily queries with 84% self-resolution rate — reducing HR workload by 45%. 📄 Document Intelligence Pipeline Automated extraction pipeline for W-2s, I-9s, offer letters, and contracts — Azure Document Intelligence + OpenCV pre-processing (OCR accuracy 67% → 89%), GPT-4o function calling with Pydantic schemas, Map-Reduce for multi-page contracts, 3-tier validation layer. Reduced document processing time by 60% and data entry errors by 72%. 🔍 Agentic Payroll Audit Agent (LangGraph POC) Autonomous audit agent using LangGraph — 6-node state graph: AnomalyAnalyser → DataFetcher (5 tools) → EvidenceEvaluator → RootCauseDeterminer → RecommendationGenerator → AuditReportWriter. Conditional edge loops back to DataFetcher if evidence insufficient (max 3 iterations). ### AI / ML Engineer @ Darwinbox Jan 2021 – Jan 2023 | Hyderabad Shipped 5 production AI features on DarwinBox's enterprise HCM platform, serving 30+ global clients including Swiggy (10,000+ employees) — owning backend data pipelines, prompt engineering, and LLM integration across the Performance Management System. ✅ Feedback Summarisation Backend pipeline for LLM-generated 360-degree feedback summaries — processing reviewer comments across reviewer_id/reviewee_id mappings with TF-IDF scoring to fit token budgets, enabling managers to consume multi-stakeholder feedback in seconds instead of hours. ✅ Auto Goal Generation Context-assembly pipeline aggregating employee role, historical performance, and team OKRs from MongoDB into structured LLM prompts. Nightly batch cron pre-computes context objects; Pydantic validation enforces SMART goal structure with JSON mode output. ✅ Pre-populate Review Comments Prompt construction pipeline retrieving past performance records, goal scores, and peer feedback via MongoDB aggregation pipelines. UX framing change (first-person → observation style) reduced manager rejection rate from 41% to 12%. ✅ MSF Summary Multi-stakeholder feedback pipeline with proportional stakeholder sampling and TF-IDF scoring when context exceeded token limits — delivering narrative LLM summaries across enterprise review cycles. ✅ Skill Generation AI-driven skill inference pipeline extracting signals from goal data, feedback keywords, and competency ratings via MongoDB aggregation. Taxonomy compliance validation ensures all inferred skills map to a 450-skill company taxonomy. Adopted by HR teams for talent gap analysis. 🔧 Infrastructure: WiredTiger compaction reduced MongoDB from 150 GB → 500 MB (99.7% reduction), query times from minutes → under 5 seconds. Cron refactoring from single-record to batch processing cut runtime from never-completing → under 10 minutes per client. ## Education ### Master of Science - MS in Computer Science The University of Texas at Arlington ### Bachelor of Technology - BTech in Computer Science Sreenidhi Institute of Science and Technology ### FIITJEE ### Middle School Diploma DRS International School ## Contact & Social - LinkedIn: https://linkedin.com/in/rithin-pallikonda-b98349154 - GitHub: https://github.com/Rithin1811?tab=repositories --- Source: https://flows.cv/rithin JSON Resume: https://flows.cv/rithin/resume.json Last updated: 2026-04-18