Konark Verma

Software Development Engineer-3

I build high-performance systems at the intersection of IoT, cloud infrastructure, and AI.

I'm always open to discussing new projects, creative ideas, or opportunities. The best way to reach me is through LinkedIn or by checking out my work on GitHub.

About Me

I'm a software engineer with a passion for building high-performance, scalable systems. With an M.Tech from IIT Delhi in Computer Science, I bring strong fundamentals in system design, algorithms, and applied AI.

Currently, I'm leading engineering efforts at DENSO Japan, Tokyo as an SDE-3, where I own system architecture and delivery for automotive software platforms. My work spans edge computing, cloud infrastructure, real-time voice AI, and developer tooling.

I enjoy working across the stack — from building CLI tools and gRPC services to designing React frontends and deploying containerized services on AWS.

Here are a few technologies I've been working with:

  • Python
  • LoRA
  • QLoRA
  • RAG
  • Small Language Models
  • Vector Search
  • Edge Deployment
  • NLP
  • MiniLM
  • Document Processing
  • gRPC
  • LLM

Experience

  1. DENSO CorporationTokyo, Japan

    Software Development Engineer-3April 2025 – Present

    Team Lead, Project Owner

    Leading projects and owning system architecture and delivery in automotive software systems.

    Software Development Engineer-2April 2022 – March 2025

    Software Engineer

  2. DIIN, Denso International IndiaGurugram, Delhi-NCR, India

    Software Development Engineer-1October 2020 – March 2022

    Software Engineer

  3. Tensor Dynamics Private LimitedIIT Delhi, Delhi, India

    Project InternOctober 2018 – December 2018

    Project Intern

  4. Plaksha Technology Leaders FellowshipGurugram, Delhi-NCR, India

    Teaching AssistantSeptember 2020 – March 2021

    Academic Support

Projects

  1. Project

    On-Device Automotive AI Assistant Platform

    A scalable platform that converts automotive documentation into deployable vehicle-specific AI assistants using a hybrid SLM + RAG architecture with query routing for optimal latency-accuracy trade-offs.

    Enabled OEMs to generate offline-capable, vehicle-specific AI assistants with sub-200ms response latency and grounded factual accuracy.

    • Python
    • LoRA
    • QLoRA
    • RAG
    • Small Language Models
    • Vector Search
    • Edge Deployment
    • NLP
    • MiniLM
    • Document Processing
  2. Project

    Quad-AI Voice Assistant System

    A real-time voice-based conversational AI orchestrator for Raspberry Pi with wake word detection, VAD, STT, TTS, LLM integration, and Acoustic Echo Cancellation. Includes MCP tool integration for synchronous and asynchronous tool execution with progress polling.

    Built a Siri-like AI assistant with LLM-powered tool orchestration and real-time voice processing.

    • Python
    • gRPC
    • LLM
    • AWS Bedrock
    • Faster Whisper STT
    • AWS Transcribe
    • Porcupine
    • AEC
    • VAD
    • AWS Polly
    • MCP
    • Docker
    • Raspberry Pi
    • OpenAI API
    • Rust
    • Tokio
  3. Project

    Quad-Terminal

    A web-based terminal for edge devices enabling interaction with Dockerized microservices via WebSockets and remote cloud access.

    Reduced cloud operational costs by ~20% and improved system performance by consolidating microservices.

    • React
    • TypeScript
    • NodeJS
    • Docker
    • AWS ECS
    • AWS ECR
    • WebSockets
    • gRPC
    • AWS CDK
    • REST APIs
    • NGINX
    • Jest
  4. Project

    Quad-Installer

    An NPM-based CLI tool for automating deployment and lifecycle management of Dockerized microservices on edge devices.

    Enabled automated deployment, remote monitoring, and self-updating infrastructure for edge systems.

    • TypeScript
    • Node.js
    • Docker
    • SystemCTL
    • AWS S3
    • AWS Cognito
    • AWS CDK
    • gRPC
    • Jest

Education

  1. 2018 - 2020

    M.Tech.Computer Science and Engineering

    Indian Institute of Technology, Delhi

  2. 2013 - 2017

    B.Tech.Computer Science

    University of Delhi

Achievements

  1. Achieved All India Rank 453 (99.6 percentile) in GATE 2018 among 107,893 candidates.

  2. Won Game Development Hackathon by redesigning 'Paratroopers' with multiple levels and power-ups using Unity3D.