---
title: "Puli Hima Vamsi Kumar - Machine Learning Engineer in Greater Bengaluru Area | Tal"
description: "Meet Puli Hima Vamsi Kumar, ML Engineer · LLM Inference · Voice AI · Multi-Agent Systems · Fine-Tuning · POC → Production at Scale · IIT Kharagpur based in Greater Bengaluru Area. AI stack includes hugging face, langchain, and langfuse. Explore public work links including medium."
image: "https://tal.club/meet/hima-vamsi-kumar-puli/share-image"
---

# Puli Hima Vamsi Kumar on Tal

## Headline

ML Engineer · LLM Inference · Voice AI · Multi\-Agent Systems · Fine\-Tuning · POC → Production at Scale · IIT Kharagpur

## About

4\+ years building and shipping AI systems in production at JustDial — not demos, not notebooks\. I work across the full AI stack: LLM inference on H100 clusters, voice bots handling live customer calls, agentic pipelines, classic ML, and computer vision — all in production at scale\. ━━━ What I've shipped ━━━ → LLM inference: Deployed Qwen3\-32B FP8, Gemma\-4\-31B, Qwen3\.5\-35B on H100 SXM using vLLM\. Pushed prefix cache hit rate from 5% → 80% by refactoring system prompts — 10× reduction in prefill compute\. Debugged FlashInfer sm90a CCCL kernel mismatch on CUDA 12\.4\. → Voice AI: Architected LiveKit voice bots for JustDial customer calls in Hinglish\. Deepgram nova\-3 STT \+ ElevenLabs TTS \+ Groq LLM\. TTFT &lt; 1\.2–1\.5s end\-to\-end\. → AI Agents: Built CS and HR chatbots with Google ADK \(multi\-turn, intent detection, RAG\)\. 13\-stage image scrutiny pipeline for listing moderation with Evidently drift monitoring\. → Computer Vision: ViT/CLIP classification → 90% reduction in manual image tagging\. YOLO \+ PaddleOCR KYC pipeline → 80% auto\-approval rate\. Processing time: hours → seconds\. → TTS Fine\-tuning: Fine\-tuned OmniVoice on Hindi studio audio \(ai4bharat/Rasa\)\. UTMOS &gt; 3\.5, speaker\-sim &gt; 0\.75\. FastAPI inference server at &lt; 80ms latency\. ━━━ Core stack ━━━ LLM Serving: vLLM, TGI, FlashInfer, PagedAttention, FP8/AWQ/GPTQ, Prefix Caching, Tensor Parallel Voice AI: LiveKit, Deepgram, ElevenLabs, WebRTC, SIP, OmniVoice, F5\-TTS Agents &amp; RAG: Google ADK, LangChain, LlamaIndex, FAISS, ChromaDB, MCP CV &amp; ML: ViT, CLIP, YOLO, PaddleOCR, Qwen\-VL Infra: Docker, Kubernetes, Prometheus, Grafana, MLflow, Evidently, Redis, FastAPI Hardware: H100 SXM, A100, NVLink, CUDA Profiling IIT Kharagpur CS, 2022\. Open to senior AI/ML roles and production AI consulting\. 📬 phvk1611@gmail\.com \| Portfolio: phvk1611\.github\.io/portfolio1

## Location

Greater Bengaluru Area

## AI stack

hugging face

langchain

langfuse

livekit

Google ADK

vLLM

## Work experience

Machine Learning Engineer at Justdial, May 2022 \- Present · 4 yrs 6 mos, Bengaluru, Building production AI systems — from GPU kernel debugging to agentic pipelines\. Deployed vLLM inference for Qwen3\-32B FP8, Gemma\-4\-31B, and Qwen3\.5\-35B\-A3B on H100 SXM; tuned to &gt;2k tok/s at P95 &lt; 2s\. Isolated dynamic variables in system prompts — pushed prefix cache hit rate from 5% → 80%, cutting redundant prefill compute by 10×\. Built agentic Customer Support and HR chatbots using Google ADK — multi\-turn context, intent detection, RAG over internal docs\. Architected LiveKit voice bot platform for JustDial business\-owner calls; TTFT &lt; 1\.2–1\.5s end\-to\-end\. Created 13\-stage image scrutiny pipeline \(NSFW, blur, watermark, OCR\-logo, duplicate\) with Prometheus monitoring and Evidently drift detection\. ViT/CLIP semantic classification: 90% reduction in manual image tagging across hotel, salon, healthcare verticals\. YOLO\+PaddleOCR KYC automation \(Aadhaar, PAN, Passport\): 80% auto\-approval rate, processing time hours → seconds\.

Summer Internship at Justdial, Apr 2021 \- Jul 2021 · 4 mos, Bengaluru, Karnataka, India

## Education

UG, Computer Science and engineering, Indian Institute of Technology, Kharagpur

Intermediate, MPC, Narayana Junior College, Nellore

## Public links

- medium: https://medium\.com/@phvk1611

[View the original profile](https://tal.club/meet/hima-vamsi-kumar-puli)

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "Person",
      "@id": "https://tal.club/meet/hima-vamsi-kumar-puli#person",
      "name": "Puli Hima Vamsi Kumar",
      "url": "https://tal.club/meet/hima-vamsi-kumar-puli",
      "image": "https://tal.club/meet/hima-vamsi-kumar-puli/profile-photo.jpg",
      "description": "Meet Puli Hima Vamsi Kumar, ML Engineer · LLM Inference · Voice AI · Multi-Agent Systems · Fine-Tuning · POC → Production at Scale · IIT Kharagpur based in Greater Bengaluru Area. AI stack includes hugging face, langchain, and langfuse. Explore public work links including medium.",
      "jobTitle": "Machine Learning Engineer",
      "worksFor": {
        "@type": "Organization",
        "name": "Justdial"
      },
      "hasOccupation": {
        "@type": "Occupation",
        "name": "Machine Learning Engineer"
      },
      "homeLocation": {
        "@type": "Place",
        "name": "Greater Bengaluru Area"
      },
      "alumniOf": [
        {
          "@type": "EducationalOrganization",
          "name": "Indian Institute of Technology, Kharagpur"
        },
        {
          "@type": "EducationalOrganization",
          "name": "Narayana Junior College, Nellore"
        }
      ],
      "knowsAbout": [
        "hugging face",
        "langchain",
        "langfuse",
        "livekit",
        "Google ADK",
        "vLLM"
      ],
      "sameAs": [
        "https://medium.com/@phvk1611"
      ],
      "mainEntityOfPage": {
        "@id": "https://tal.club/meet/hima-vamsi-kumar-puli#webpage"
      }
    },
    {
      "@type": "ProfilePage",
      "@id": "https://tal.club/meet/hima-vamsi-kumar-puli#webpage",
      "url": "https://tal.club/meet/hima-vamsi-kumar-puli",
      "name": "Puli Hima Vamsi Kumar on Tal",
      "description": "Meet Puli Hima Vamsi Kumar, ML Engineer · LLM Inference · Voice AI · Multi-Agent Systems · Fine-Tuning · POC → Production at Scale · IIT Kharagpur based in Greater Bengaluru Area. AI stack includes hugging face, langchain, and langfuse. Explore public work links including medium.",
      "dateModified": "2026-11-11T13:54:41.567Z",
      "isPartOf": {
        "@id": "https://tal.club/#website"
      },
      "mainEntity": {
        "@id": "https://tal.club/meet/hima-vamsi-kumar-puli#person"
      },
      "primaryImageOfPage": {
        "@type": "ImageObject",
        "url": "https://tal.club/meet/hima-vamsi-kumar-puli/profile-photo.jpg",
        "contentUrl": "https://tal.club/meet/hima-vamsi-kumar-puli/profile-photo.jpg",
        "caption": "Puli Hima Vamsi Kumar profile photo on Tal"
      },
      "inLanguage": "en-IN"
    }
  ]
}
```
