Summary
Overview
Work History
Education
Skills
Websites
Timeline
Generic

Hema Varun Kumar Penaganti

Summary

Senior AI/ML Engineer with expertise in building large-scale AI applications and LLM-powered systems. Designs production-grade GenAI systems and scalable ML infrastructure on cloud platforms. Experienced in observability and enterprise AI deployments, enhancing performance for thousands of users. Focused on innovative AI system design and advanced multi-agent architectures.

Overview

7
7
years of professional experience

Work History

Senior AI/ML Engineer

Tiger Analytics Private Limited
Chennai
08.2022 - Current
  • Designed and built enterprise chatbot platforms integrated with Google Chat and Microsoft Teams.
  • Implemented chatbot solutions using Rasa and Microsoft Bot Framework to support workflow automation for managers.
  • Developed bots enabling managers to create and track ClickUp tickets, view ticket status, priorities, due dates, and manage task assignments.
  • Built scalable chatbot architectures enhancing client onboarding and demo solutions.
  • Explored and evaluated multiple vector databases including Milvus, Weaviate, Chroma, and Qdrant.
  • Provided architectural guidance to internal teams on vector database selection and implementation for RAG-based applications.
  • Conducted technical evaluations and performance comparisons to determine optimal vector search solutions.
  • Designed and implemented a large-scale AI voice assistant for retail store employees deployed across 3,000+ stores.
  • Built a FastAPI-based AI service enabling employees to recommend products, answer customer queries, and provide company policy guidance.
  • Integrated Azure OpenAI GPT models to power natural language interactions.
  • Developed a high-performance RAG pipeline using Azure AI Search to support knowledge retrieval across 650K+ product catalog entries.
  • Built automated pipelines for continuous product data updates and indexing.
  • Implemented monitoring pipelines ensuring response quality, system performance, and AI model outputs.
  • Optimized API performance using async Python, improving response latency and scalability.
  • Initially deployed on Azure App Service, later migrated to Azure Kubernetes Service (AKS) for improved scalability and orchestration.
  • Python, FastAPI, Azure OpenAI, Azure AI Search, Redis, Azure Blob Storage, Azure Databricks, AKS
  • Developed an MCP Server to support tool access across multiple AI agents.
  • Implemented OpenTelemetry-based logging and observability for monitoring agent interactions and system performance.
  • Deployed scalable services on Azure Kubernetes Service (AKS).
  • Built a Graph-RAG powered multi-agent system using LangGraph to assist business teams in identifying tasks at risk and recommending mitigation strategies.
  • Currently building framework-agnostic multi-agent systems using the A2A (Agent-to-Agent) protocol to enable scalable and interoperable AI agent ecosystems.
  • Explored distributed training and fine-tuning techniques for Large Language Models (LLMs) to enhance scalability and model performance.

ML Engineer

BusinessOnBot Pvt Ltd
Bengaluru
08.2021 - 08.2022
  • Developed conversational AI chatbots for e-commerce brands, enhancing customer engagement on WhatsApp.
  • Designed NLP pipelines using Rasa to improve user shopping experiences via conversational interfaces.
  • Analyzed conversational data to refine chatbot flows, boosting response accuracy and user satisfaction.
  • Created robust NLU models to address ambiguous user queries, strengthening intent recognition capabilities.

ML Engineer

Innova Solutions Private Limited
Hyderabad
07.2019 - 08.2021
  • Developed enterprise chatbots for Slack and Microsoft Teams using Rasa and Microsoft Bot Framework to enhance user engagement.
  • Built ETL automation tools for refreshing production data into development environments, streamlining data accessibility for testing.
  • Developed automation tools for database migration and schema deployment, ensuring seamless transitions and minimal downtime.

Education

B.Tech - Electronics And Communication Engineering

Indian Institute of Technology, Roorkee
Roorkee, Uttarakhand
07-2018

Skills

Programming: Async
Python, Python
AI / Machine Learning: Deep
Learning, LLM Applications, Machine
Learning, Multi- Agent Systems, NLP, Retrieval
Augmented Generation(RAG)
Frameworks & Libraries: Autogen, CrewAI, FastAPI, Keras, LangGraph, Microsoft
Bot Framework, Microsoft
Framework, NLTK, NumPy, Pandas, Pydantic
AI, Pytorch, Rasa, Scikit-Learn, SpaCy, RAGAS, DeepEval, Azure AI Evaluation
GenAI & Vector Systems: Azure OpenAI, Embeddings, Semantic Search, Vector Databases (Milvus, Weaviate,
Qdrant, Chroma)
Cloud & Infrastructure: Azure
App Service, Azure Blob Storage, Azure
Databricks, Azure Functions, Azure Kubernetes Service(AKS)
Observability: Azure
Monitor, Dynatrace, Grafana, Logging
& Monitoring pipelines, OpenTelemetry, Prometheus
Databases: Azure AI
Search, MySQL, Oracle
SQL, Redis

Cloud architecture

Timeline

Senior AI/ML Engineer

Tiger Analytics Private Limited
08.2022 - Current

ML Engineer

BusinessOnBot Pvt Ltd
08.2021 - 08.2022

ML Engineer

Innova Solutions Private Limited
07.2019 - 08.2021

B.Tech - Electronics And Communication Engineering

Indian Institute of Technology, Roorkee
Hema Varun Kumar Penaganti