---
title: "RAKSHITH KUMAR KN - SDE 2 AI/ML in Bengaluru | Tal"
description: "Meet RAKSHITH KUMAR KN, Senior AI Engineer | LLMOps & Production AI Systems | Multi-Agent Orchestration & RAG | LangGraph, vLLM & TensorRT | AWS Bedrock & Distributed Systems | Bengaluru based in Bengaluru. AI stack includes anthropic apis, claude code, and cursor. Explore public work links includi..."
image: "https://tal.club/meet/rakshith-kumar/share-image"
---

# RAKSHITH KUMAR KN on Tal

## Headline

Senior AI Engineer \| LLMOps & Production AI Systems \| Multi\-Agent Orchestration & RAG \| LangGraph, vLLM & TensorRT \| AWS Bedrock & Distributed Systems \| Bengaluru

## About

🚀 4 hours → 2 seconds\. I build AI systems that make that kind of production impact\. I’m a Senior AI/ML & Generative AI Engineer with 5\+ years of software engineering experience, specializing in production LLM systems, agentic AI, AI infrastructure, and high\-performance inference\. 💡 $2\.3M\+ measurable business impact \| 99\.99% uptime \| 85% reduction in manual context\-fetching latency I bridge the gap between experimental AI and reliable, scalable production systems—taking models from notebooks to low\-latency APIs and enterprise\-grade platforms\. 🚀 What I’m Building Agentic AI & MCP • Production MCP servers connecting multi\-agent systems to enterprise tools such as HappyFox and Jira • Reduced manual context\-fetching latency by 85% LLM Evaluation & Distillation • GPT\-4\-supervised evaluation and knowledge\-distillation pipelines on B100 GPUs • Compressed enterprise firewall validation from 4\+ hours → 2–5 seconds • Achieved zero LLM inference cost in the production validation workflow Advanced Retrieval & AI Systems • 5\-stage confidence\-gated agent architectures • Hybrid semantic search \+ NL\-to\-SQL • p95 latency <300ms for supply\-chain intelligence workloads ⚙️ Core Technical Expertise Generative AI: Multi\-Agent Systems, LLMs, RAG, GraphRAG, LangGraph, DSPy, Tool Calling, MCP, NeMo Guardrails AI Infrastructure & Inference: vLLM, TensorRT\-LLM, GPU Inference, B100, A100, L4, Continuous Batching, Kubernetes, AWS Bedrock, GCP Vertex AI Evaluation & Alignment: LLM\-as\-a\-Judge, RAGAS, RLHF, DPO, LoRA, QLoRA, 72B\+ parameter models Production Engineering: Python, FastAPI, Docker, Kubernetes, AWS, GCP, Distributed Systems, MLOps, High\-Availability Architecture 🏢 Enterprise & Compliance I build fault\-tolerant AI systems for regulated environments, including: • 99\.99% uptime for HIPAA\-compliant infrastructure • 2 healthcare audits, zero findings • NLP pipelines processing 50,000\+ financial documents with zero PII leakage • Production systems across enterprise security, healthcare, and financial services 🏆 Recognition • Co\-author — IEEE ACAI 2022 • Winner — AI Help Desk Hackathon • Winner — AI Doctor Analyzer Hackathon 🎯 Open to Opportunities I’m currently exploring: Senior AI Engineer \| Senior Applied AI Engineer \| AI Platform Engineer \| GenAI Engineer \| AI Infrastructure Engineer I’m particularly interested in product companies solving difficult architectural problems and scaling AI systems from prototype to production\. 📩 Let’s connect: rakshitkumarkn@gmail\.com

## Location

Bengaluru

## AI stack

anthropic apis

claude code

cursor

hugging face

langchain

langgraph

## Work experience

SDE 2 AI/ML at Gruve, Sep 2025 \- Present · 1 yr 1 mo, Région métropolitaine de Bangalore, Building production GenAI systems and distributed ML infrastructure for Fortune 500 enterprises\. Key projects: • Firewall Validation — LLM\-supervised Knowledge Distillation \(GPT\-4 Teacher → distilled student ensemble\)\. 4\+ hours → 2–5 seconds\. Zero LLM calls at inference\. 200\+ firewalls, 10× faster migration\. • AI/NLP Redaction — Zero PII leakage\. SOC 2 passed\. 99\.2% precision at 2,000\+ docs/day\. • Enterprise AI Search — Neo4j \+ Qdrant hybrid\. 10K\+ QPD at p95 <300ms\. 99\.9% uptime\. • Azure Migration — 62% cost reduction \($18K/month\) via event\-driven Container Apps\. • TechGenie Voice Agent — 80\+ ticket types, 42% faster resolution, 3 enterprise clients\. Stack: GPT\-4 · Claude 3\.5 · PyTorch · BERT · LangGraph · Neo4j · Qdrant · AWS Bedrock · ECS · Lambda · SQS · FastAPI · Azure · Docker · Kubernetes

Artificial Intelligence Engineer at August AI, Aug 2024 \- Aug 2025 · 1 yr 1 mo, Bengaluru, Karnataka, India, • Architected a multi\-agent AI system for automated patient interviews and clinical report summarization, reducing clinician administrative burden by 45% and processing 2,500\+ daily interactions across 3 major healthcare facilities\. • Optimized LLM memory management and prompt engineering for extended medical conversations, improving context retention and diagnostic accuracy by 75%; achieved 91% accuracy across 5,000\+ patient sessions, cutting initial consultation time by 40%\. • Engineered NLP\-driven medical documentation pipelines achieving 97% accuracy across 10,000\+ clinical documents monthly, delivering $150K annual cost savings through reduced manual review\. • Deployed HIPAA\-compliant AI infrastructure on AWS and Azure with end\-to\-end encryption and RBAC, sustaining 99\.99% uptime for 500\+ concurrent users through all enterprise regulatory audits\.

Machine Learning Engineer at Snive, Feb 2024 \- Aug 2024 · 7 mos, Région métropolitaine de Bangalore, Machine Learning Engineer Snive \(Krut AI\), BengaluruJan 2024 – Aug 2024 • Implemented Fast UNet and VAE optimizations for SDXL \+ ControlNet, reducing inference time to 1–2 seconds and cutting e\-commerce client content creation costs by 80%; pipeline processed 50,000\+ product images monthly\. • Reduced GPU memory consumption by 60% via gradient checkpointing and mixed\-precision training, enabling costefficient scaling and saving $30K/month in AWS G4/G5 infrastructure costs\.

Associate Data scientist at Lincode India, Sep 2022 \- Feb 2024 · 1 yr 6 mos, Bangalore, • Delivered OCR, image segmentation, and object detection models for 8 international manufacturing clients, achieving 92% OCR accuracy at 0\.25s inference and a 25% improvement in production quality control across automotive and electronics sectors Replaced redundant polling with server\-sent events for real\-time inference updates, cutting API infrastructure costs by 90% and generating $2M in annual savings across 15\+ global facilities processing 50,000\+ components daily\.

Data Science Intern at Lincode India, Mar 2022 \- Sep 2022 · 7 mos, Bengaluru, Karnataka, India, Lincode is an Artificial Intelligence & Industrial IoT solutions company increasing the profitability of manufacturing companies globally\.

Research Scholar \- Data science at MENMOZHI TECHNOLOGIES, Dec 2021 \- Mar 2022 · 4 mos, Бангалор Сельский

## Education

Msc, big data analytics, St Joseph's University

Bachelor of Computer application \- BCA, Coder, Sheshadripuram Arts, Science & Commerce College, Sheshadripuram , Bangalore\-20

## Public links

- github: https://github\.com/rakshit176
- rakshith\-kumar\-kn\-ai\-engineer\-portf\.vercel\.app: https://rakshith\-kumar\-kn\-ai\-engineer\-portf\.vercel\.app/

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

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "Person",
      "@id": "https://tal.club/meet/rakshith-kumar#person",
      "name": "RAKSHITH KUMAR KN",
      "url": "https://tal.club/meet/rakshith-kumar",
      "image": "https://tal.club/meet/rakshith-kumar/profile-photo.jpg",
      "description": "Meet RAKSHITH KUMAR KN, Senior AI Engineer | LLMOps & Production AI Systems | Multi-Agent Orchestration & RAG | LangGraph, vLLM & TensorRT | AWS Bedrock & Distributed Systems | Bengaluru based in Bengaluru. AI stack includes anthropic apis, claude code, and cursor. Explore public work links includi...",
      "jobTitle": "SDE 2 AI/ML",
      "worksFor": {
        "@type": "Organization",
        "name": "Gruve"
      },
      "hasOccupation": {
        "@type": "Occupation",
        "name": "SDE 2 AI/ML"
      },
      "homeLocation": {
        "@type": "Place",
        "name": "Bengaluru"
      },
      "alumniOf": [
        {
          "@type": "EducationalOrganization",
          "name": "St Joseph's University"
        },
        {
          "@type": "EducationalOrganization",
          "name": "Sheshadripuram Arts, Science & Commerce College, Sheshadripuram , Bangalore-20"
        }
      ],
      "knowsAbout": [
        "anthropic apis",
        "claude code",
        "cursor",
        "hugging face",
        "langchain",
        "langgraph"
      ],
      "sameAs": [
        "https://github.com/rakshit176",
        "https://rakshith-kumar-kn-ai-engineer-portf.vercel.app/"
      ],
      "mainEntityOfPage": {
        "@id": "https://tal.club/meet/rakshith-kumar#webpage"
      }
    },
    {
      "@type": "ProfilePage",
      "@id": "https://tal.club/meet/rakshith-kumar#webpage",
      "url": "https://tal.club/meet/rakshith-kumar",
      "name": "RAKSHITH KUMAR KN on Tal",
      "description": "Meet RAKSHITH KUMAR KN, Senior AI Engineer | LLMOps & Production AI Systems | Multi-Agent Orchestration & RAG | LangGraph, vLLM & TensorRT | AWS Bedrock & Distributed Systems | Bengaluru based in Bengaluru. AI stack includes anthropic apis, claude code, and cursor. Explore public work links includi...",
      "dateModified": "2026-09-18T05:58:29.997Z",
      "isPartOf": {
        "@id": "https://tal.club/#website"
      },
      "mainEntity": {
        "@id": "https://tal.club/meet/rakshith-kumar#person"
      },
      "primaryImageOfPage": {
        "@type": "ImageObject",
        "url": "https://tal.club/meet/rakshith-kumar/profile-photo.jpg",
        "contentUrl": "https://tal.club/meet/rakshith-kumar/profile-photo.jpg",
        "caption": "RAKSHITH KUMAR KN profile photo on Tal"
      },
      "inLanguage": "en-IN"
    }
  ]
}
```