---
title: "Janakiraman K - Founder in Tiruvallur | Tal"
description: "Meet Janakiraman K, Agentic AI Engineer | Multi-Agent Systems · LLM Orchestration · Production RAG | GCP · LangGraph · AutoGen | 11x Hackathon Winner | Open to Full-Time AI/ML Roles based in Tiruvallur. AI stack includes hedra, langsmith, and meta."
image: "https://tal.club/meet/janakiraman/share-image"
---

# Janakiraman K on Tal

## Headline

Agentic AI Engineer \| Multi\-Agent Systems · LLM Orchestration · Production RAG \| GCP · LangGraph · AutoGen \| 11x Hackathon Winner \| Open to Full\-Time AI/ML Roles

## About

Most AI engineers build wrappers\. I build the engine underneath\. I'm an Agentic AI Engineer who spent the last 2\+ years making LLMs actually useful — not just responsive\. That means systems that plan across steps, delegate to tools, retain context across sessions, and ship to production without falling apart\. Here's what that looks like in practice: → Built production RAG pipelines achieving 90–93% retrieval accuracy — 30%\+ above keyword\-only baselines — using FAISS, hybrid retrieval, and semantic chunking → Cut LLM inference latency by 20–30% through async agent execution and prompt routing on GCP Vertex AI \+ GKE → Designed multi\-agent orchestration workflows with LangGraph and AutoGen that handle real\-world complexity: branching decisions, tool delegation, and stateful memory across long sessions → Won 11 hackathons \(5x Web3, 6x Web2\) — competing and shipping under pressure, not just prototyping I don't just study agentic AI\. I debug it at 2am when it behaves non\-deterministically, ship it when it's ready, and iterate when it's not\. What I work with: Agentic frameworks: LangGraph · AutoGen · LangChain Infrastructure: GCP \(Vertex AI, GKE\) · Docker · FastAPI Retrieval & memory: FAISS · pgvector · semantic chunking · hybrid search Languages: Python · Solidity Currently building: AutoAgent \(NL\-to\-agent executor\) · G3 Dev Hub \(decentralized GitHub alternative\) Currently open to full\-time AI/ML Engineering roles — particularly teams working on frontier agent systems, LLM infrastructure, or production\-scale AI products\. If you're building something that needs more than a wrapper, let's talk\. Reach me at janakiramankeerthivelan1021@gmail\.com or connect here on LinkedIn\.

## Location

Tiruvallur

## AI stack

hedra

langsmith

meta

metaai

## Work experience

Founder at Crypto\-Cortex\-Crew, Oct 2024 \- Present · 1 yr 9 mos, Tiruvallur, Tamil Nadu, India, Built and launched a Web3 security research collective, winning 5 Web3 hackathons, by leading end\-to\-end system design, team coordination, and competitive technical execution\. Architecting G3 Dev Hub — a decentralized, on\-chain GitHub alternative — by designing a tokenized repository ownership model on top of a distributed storage layer\. Pioneering AutoAgent, an NL\-to\-agent framework that converts natural language instructions into autonomous task executors, using LangGraph for stateful multi\-step workflow orchestration\.

Python Developer at Altruisty, Jun 2025 \- Dec 2025 · 7 mos, Hybrid, Delivered Python\-based backend services and automation pipelines, reducing manual processing time by building scalable, modular workflow components integrated with existing production systems\. Contributed to data engineering tasks including ETL pipeline design, API integration, and structured data handling to support downstream ML feature pipelines\.

Software Application Developer at SecureDApp \- Blockchain & Web3 Security, Dec 2024 \- Mar 2025 · 4 mos, Hybrid, Developed smart contract security tooling and application\-layer features for a Web3 security platform, contributing to vulnerability detection workflows across Solidity\-based contracts\. Collaborated on blockchain security research, applying static analysis techniques to surface contract\-level risks — directly supporting the audit pipeline used by enterprise clients\.

AI Developer at McZeal, Jan 2024 \- Dec 2024 · 1 yr, Chennai Nungambakkam, Achieved 90–93% retrieval accuracy on a production RAG system by implementing FAISS\-based hybrid retrieval with semantic chunking — a 30%\+ improvement over keyword\-only baseline\. Reduced LLM response latency by 20–30% across multi\-agent workflows by optimizing prompt routing, parallelizing agent execution, and migrating inference workloads to GCP Vertex AI\. Built and mentored a team of junior AI developers, delivering client\-facing AI tools including a memory\-augmented LLM assistant and an internal automation suite — both shipped to production\.

## Education

Bachelor of Technology \- BTech, Information Technology, jaya engineering college

bharathidasan matriculation higher secondary school

[View the original profile](https://tal.club/meet/janakiraman)

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "Person",
      "@id": "https://tal.club/meet/janakiraman#person",
      "name": "Janakiraman K",
      "url": "https://tal.club/meet/janakiraman",
      "image": "https://tal.club/meet/janakiraman/profile-photo.jpg",
      "description": "Meet Janakiraman K, Agentic AI Engineer | Multi-Agent Systems · LLM Orchestration · Production RAG | GCP · LangGraph · AutoGen | 11x Hackathon Winner | Open to Full-Time AI/ML Roles based in Tiruvallur. AI stack includes hedra, langsmith, and meta.",
      "jobTitle": "Founder",
      "worksFor": {
        "@type": "Organization",
        "name": "Crypto-Cortex-Crew"
      },
      "hasOccupation": {
        "@type": "Occupation",
        "name": "Founder"
      },
      "homeLocation": {
        "@type": "Place",
        "name": "Tiruvallur"
      },
      "alumniOf": [
        {
          "@type": "EducationalOrganization",
          "name": "jaya engineering college"
        },
        {
          "@type": "EducationalOrganization",
          "name": "bharathidasan matriculation higher secondary school"
        }
      ],
      "knowsAbout": [
        "hedra",
        "langsmith",
        "meta",
        "metaai"
      ],
      "mainEntityOfPage": {
        "@id": "https://tal.club/meet/janakiraman#webpage"
      }
    },
    {
      "@type": "ProfilePage",
      "@id": "https://tal.club/meet/janakiraman#webpage",
      "url": "https://tal.club/meet/janakiraman",
      "name": "Janakiraman K on Tal",
      "description": "Meet Janakiraman K, Agentic AI Engineer | Multi-Agent Systems · LLM Orchestration · Production RAG | GCP · LangGraph · AutoGen | 11x Hackathon Winner | Open to Full-Time AI/ML Roles based in Tiruvallur. AI stack includes hedra, langsmith, and meta.",
      "dateModified": "2026-07-18T17:36:57.075Z",
      "isPartOf": {
        "@id": "https://tal.club/#website"
      },
      "mainEntity": {
        "@id": "https://tal.club/meet/janakiraman#person"
      },
      "primaryImageOfPage": {
        "@type": "ImageObject",
        "url": "https://tal.club/meet/janakiraman/profile-photo.jpg",
        "contentUrl": "https://tal.club/meet/janakiraman/profile-photo.jpg",
        "caption": "Janakiraman K profile photo on Tal"
      },
      "inLanguage": "en-IN"
    }
  ]
}
```