ANKUR KOHLI
I am a Software Engineer specializing in AI and GenAI/LLM engineering, focused on
architecting scalable, intelligent, and high performance systems with clean, production ready architecture. I
have hands on experience developing cross platform frontend and realtime, multithreaded backend systems at an
Italian MediaTech organization, delivering responsive applications used in real operational environments. With
expertise in Python, C/C++, Java, JavaScript, React, Dart (Flutter), and API driven architectures, I design
and deploy resilient software across mobile, web, and distributed platforms.
I have extensive experience engineering realtime distributed systems using Dockerized architectures, ROS2
pipelines, GitLab CI/CD automation, and structured integration workflows, improving system reliability,
deployment efficiency, and runtime stability. My work emphasizes modular design, low latency communication,
and hardware agnostic scalability, validated through production deployment. I leverage GenAI technologies
including LLM, RAG, and LlamaIndex to build intelligent, scalable systems enabling efficient data processing,
automation, and secure client server communication.
I am passionate about developing maintainable software, optimizing backend architectures, and delivering
intuitive frontend systems. I value collaboration, disciplined engineering, and continuous improvement, and I
am committed to advancing reliable, scalable, and intelligent software through robust integration, automation,
and modern software engineering practices.
Experience
Career Identity
Software Engineer with expertise in Python, C/C++, JavaScript, ReactJS, Dart, Flutter, Java, Tailwind CSS & API driven distributed systems, focused on advanced technologies
Professional Experience
- Developed and managed cross platform frontends with a UI/UX focus and realtime, multithreaded backends, enabling secure low latency communication and improving system responsiveness by 25%.
- Led the development and deployment of an autonomous NAV2 SLAM pipeline using automation pipelines tested on a real robot, reducing deployment time by 30% and enabling scalable multiplatform deployment.
- Enhanced system reliability through structured integration testing, validation, and debugging workflows using GitLab CI/CD, which reduced post deployment errors by 40% and improved runtime stability.
- Drove agile cross team collaboration through technical documentation, architectural design, and specifications, turning research concepts into deployable, high performance systems.
- Developed realtime, multithreaded arch to ensure low latency performance and improved system efficiency by 30% for intelligent robotic systems.
- Prototyped SLAM-based mapping and navigation pipelines within Dockerized ROS2 environments, establishing a foundation for scalable CI/CD deployments.
- Tested, validated, and debugged software using GitLab CI/CD, increasing system reliability and uptime by 20%.
- Authored comprehensive technical documentation, improving team productivity and maintainability across projects.
Professional Certifications
Professional certifications and credentials that validate my expertise
Prompt Design in Vertex AI
Google Cloud
February 2026
Azure Fundamentals
Microsoft
November 2025
Introduction to Responsible AI
Google Cloud
January 2025
Responsible AI: Applying AI Principles with Google Cloud
Google Cloud
January 2025
Innovating with Google Cloud AI
Google Cloud
December 2024
Introduction to Generative AI
Google Cloud
October 2024
Introduction to Machine Learning: Art of the Possible
Amazon Web Services (AWS)
September 2024
Introduction to Robotics on AWS
Amazon Web Services (AWS)
September 2024
Project Demos
Real-world implementations — click any demo to expand and explore
Projects Experience
ResumeAI: Next-Gen Career Intelligence Platform
An AI assisted resume analysis platform built with React.js, Tailwind CSS, and Puter.js, designed to provide cost efficient ATS style insights. The platform performs semantic resume job description matching, highlights skill gaps, and generates actionable improvement suggestions through GenAI integration, with a strong focus on accessibility for individuals and smaller teams.
SkyScope Live Weather Dashboard with API Integration
A fully interactive weather platform that delivers real-time forecasts, AQI metrics, and dynamic visual effects based on live conditions. Developed using JavaScript, Bootstrap, and Canvas animations, the app adapts its UI to weather and time of day, creating an engaging and responsive user experience.
Interactive Game using JavaScript
A lightweight, browser-based Rock-Paper-Scissors game built using plain HTML, CSS, and JavaScript. The project focuses on simple UI, clean structure, and beginner-friendly logic that clearly demonstrates DOM manipulation and event handling.
Responsive Website Design
A Restaurant website developed using HTML, CSS, and some minor functions in JavaScript, demonstrating front-end development skills and basic web design principles.
3D reconstruction
To developed immersive virtual reality experiences of robotics by capturing and converting real-world objects or environments into detailed 3D models.
Cervical Cancer Detection using CNN & VGG16 Module
Leveraging deep learning models like VGG16 to classify cervical cancer in medical images, such as Pap smear slides, due to its proven effectiveness in image recognition tasks.
Software Architecture for Mobile Robot Control
Developing a software architecture for controlling a mobile robot by applying graph-based routing and Dijkstra's, using ROS, Gazebo, and RViz. Includes ROS nodes in Python: a controller and a UI.
Reinforcement Learning using A2C & PPO for Lunar Lander
Implemented solutions for the Lunar Lander problem using Advantage Actor-Critic (A2C) and Proximal Policy Optimization (PPO) algorithms, focusing on optimizing policy via policy iteration approaches and value functions.
