App LogoApp name
VY

Vamshi Yelagandula

Open to work3 years experience

AI Engineer

Bangalore, IndiaTarget Roles: Backend Engineer • Full-Stack Developer • Frontend Specialist

AI Engineer

GitHub

Standing Rank

Rank Not Available

Developer Badges

No badges earned yet

Skills & Technologies

36 skills
generative aillmslangchainlanggraphopenai apihugging facetransformersrag pipelinesprompt engineeringai agentsmulti-agent systemsllm observabilityfine-tuningfastapistreamlitlangsmithgroq sdktavily searchbeautifulsoupfaisschromadbembedding pipelinespythonpandassqljsoncsv processingdata wranglingrest apisawsec2s3iamgitgithubci/cd

GitHub Activity Evidence

GitHub Footprint Not Connected

Recruiters value verified code contributions. Linking a GitHub account displays live heatmaps, active contribution metrics, repository languages, and push activity tags.

Work Experience

AI Engineer

Fractal Analytics

Jan 2025 - Present Bangalore
  • Developed LLM-powered decision intelligence pipelines using LangChain and LangGraph for multi-step autonomous reasoning in business analytics, accelerating report generation by ~40%.
  • Built multi-agent AI systems coordinating specialised agents (research, retrieval, synthesis) using LangGraph state machines to automate complex enterprise workflows, reducing completion time by ~35%.
  • Engineered production RAG pipelines with FAISS and HuggingFace embeddings for enterprise knowledge bases, improving retrieval precision by ~30% through optimised chunking strategies.
  • Deployed FastAPI microservices exposing AI pipelines to analytics dashboards — supporting 500+ daily API calls with <200 ms response time — and hosted apps on AWS EC2/S3.
  • Implemented end-to-end LLM observability with LangSmith and integrated multimodal document AI for automated structured data extraction from PDFs and invoices.

AI Engineer

Yellow.ai

Jun 2023 - Dec 2024 Bangalore
  • Designed and deployed conversational AI agents for enterprise CX automation using LangChain, handling 10,000+ monthly customer queries with ~85% self-service containment rate.
  • Built RAG-based Knowledge Base pipelines (WebBaseLoader, HuggingFace embeddings, FAISS) improving answer relevance by ~40% over keyword baselines and reducing query latency by ~30%.
  • Developed tool-orchestrated LLM agents with intelligent query routing (primary RAG + real-time web search fallback), domain validation, and multi-turn history for secure, contextual responses.
  • Exposed conversational AI pipelines as FastAPI REST microservices integrating with enterprise CRM/helpdesk platforms; leveraged LangSmith tracing to cut debugging time by ~50%.

Projects

Multi-Agent AI Research System Autonomous Research Pipeline

LangChainTavily APIBeautifulSoupGroq LLaMA 3.3 70B
  • Architected a sequential multi-agent pipeline (LangChain create_react_agent) with Search Agent (Tavily API), Reader Agent (BeautifulSoup scraping), Writer Chain (Groq LLaMA 3.3 70B) synthesising structured reports, and Critic Chain delivering automated quality scoring.

ICICI Bank Customer Support Assistant RAG-Based Banking Chatbot

StreamlitRAGWebBaseLoaderHuggingFaceFAISSTavily
  • Built an AI-powered chatbot using Streamlit with a full RAG pipeline (WebBaseLoader, HuggingFace, FAISS), intelligent query routing with Tavily web search fallback, domain validation, and multi-turn chat history.

InvoiceIQ Smart Invoice Data Extractor

StreamlitPyMuPDFGroq Llama 4 VisionJSONCSV
  • Built a Streamlit app for GST invoice PDF upload with automatic structured data extraction using PyMuPDF rasterisation and Groq Llama 4 Vision; enforced strict validation for IRN, GSTIN, and numeric fields with JSON/CSV export.

Leaderboard Standings

Leaderboard Position Pending

Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.

Assessment Highlights

Assessments Not Completed

Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.

AI Collaboration Score

AI Collaboration Score Pending

Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.

Role Compatibility Profile

Role Compatibility Analysis Pending

Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.

Achievements

Achievements Not Earned

Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.

About Details

Professional Bio

Results-driven AI Engineer with 3 years of experience in Large Language Models, RAG architectures, and production-grade AI applications. Proven track record building end-to-end GenAI solutions using LangChain, LangGraph, OpenAI, FastAPI, and AWS.

B.Tech in Mechanical Engineering

Anurag Group of Institutions (2017 - 2021)

Languages: English, Hindi