Open to opportunities · Manchester, UK

RohanInamdar

AI Engineer & Researcher. Motivated by the hardest, most challenging and multidisciplinary problems — from safe autonomous systems and 3D perception to LLMs and quantitative reasoning. MSc Artificial Intelligence @ University of Manchester.

View My Work Get In Touch Google Scholar GitHub
4+
Publications
2
Patents Filed
8+
Citations
5+
Research Labs
3
Countries
01

About Me

Current Position
MSc Artificial Intelligence
University of Manchester, Expected 2026
Undergraduate
B.Tech Electronics & Computer Engineering
VIT Chennai · CGPA 8.38/10 · 2021–2025
Research Focus
Safe RL · Semantic Segmentation · 3D Point Clouds · LLMs · Autonomous Systems · Robotics

I'm an AI engineer and researcher driven by a passion for challenging, multidisciplinary problems. During my B.Tech at VIT Chennai, I built one of the most extensive research records in my cohort — authoring 4 publications across IEEE Access, Elsevier and international conferences, filing 2 patents, conducting funded research across labs in India and South Korea, and presenting at conferences as far afield as Minsk, Belarus.

My work spans an unusually wide range: safe reinforcement learning for autonomous vehicles, semantic segmentation of satellite imagery, 3D point cloud classification for AR/VR, robotic arm design, voice-enabled navigation, agri-robotics and deepfake detection. I'm genuinely drawn to problems that refuse to stay within one discipline.

I'm motivated to work on the hardest research topics — problems that sit at the intersection of multiple fields, demand rigorous thinking, and create meaningful real-world impact. Whether building LLM pipelines, quantitative models, autonomous systems or data-driven products, I bring the same depth and drive.

Currently at the University of Manchester pursuing MSc AI, I am actively seeking full-time roles in LLM engineering, data analysis, quant research and ML engineering.

Reinforcement LearningLLMs & NLPComputer VisionRobotics / ROS23D Point CloudsAutonomous SystemsPyTorchData AnalysisQuantitative ModellingMultidisciplinary Research
[LLM]
LLM Engineer
Fine-tuning, RAG pipelines, prompt engineering and production AI systems.
[DATA]
Data Analyst
Statistical modelling, data pipelines and insight-driven decision making.
[QUANT]
Quant Analyst
ML-based financial modelling, algorithmic thinking and quantitative strategy.
[ML]
ML / Research Engineer
Deep learning architecture, training pipelines and cutting-edge AI research.
02

Research Experience

Fall 2023 –
Present
SENSE Lab, VIT Chennai
Researcher — Safe RL & Semantic Segmentation
  • Researched safe trajectory planning for self-driving vehicles using constrained Reinforcement Learning
  • Developed a hybrid UNet + Swin Transformer model for precise satellite image segmentation
  • Building a unified lightweight model covering aerial, ground and underwater datasets
  • Mentored by Prof. Nitish Katal; contributed to 2 published journal papers from this lab
Chennai, India
Summer
2024
Jeonbuk National University
Research Intern — 3D Object Classification (AR/VR)
  • Funded by Korea Environmental Industry and Technology Institute (KEITI)
  • Designed a lightweight Point Cloud Network for 3D object classification in AR/VR environments
  • Model outperformed the SOTA baseline by 1.4% on benchmark datasets
  • Guided by Prof. R. Karthik and Prof. Jaehyuk Cho
Jeonju, South Korea
Winter –
Summer 2024
SENSE Lab, VIT Chennai
Researcher — Robot Hand & Navigation Error Rerouting
  • Designed a voice-enabled rerouting system for autonomous robot navigation failure recovery
  • Tested on TurtleBot3 Waffle using the ROS2 Nav2 stack in real and simulated environments
  • Engineered a precision robot hand for fine manipulation tasks — filed as Indian patent #202441087748
Chennai, India
Fall 2023
NAHEP — World Bank / ICAR Funded
Research & Teaching Assistant — AgriBot
  • Developed an autonomous AgriBot for pest and disease detection in organic farming
  • Designed robotic arm and voice-enabled navigation for field deployment
  • Taught a 2-week intensive course on Python, ML and Robotics to 10 international MSc/PhD students
Parbhani, India
Summer
2023
VIT Chennai
Researcher — Deep Reinforcement Learning Navigation
  • Trained a LiDAR-equipped mobile robot in ROS2 Gazebo 11 using the TD3 algorithm
  • Achieved 82% autonomous navigation accuracy for obstacle avoidance in dynamic environments
  • Used PyTorch and TensorBoard for training pipeline monitoring and visualisation
Chennai, India
03

Publications & Patents

Journal · IEEE Access
Point Cloud-based 3D Object Classification with Non-local Attention and Lightweight CNN
R. Karthik, Rohan Inamdar, S. Kavin Sundarr, J. Cho, V. E. Sathishkumar
View Paper
Journal · E-Prime, Elsevier
A Comprehensive Review on Safe Reinforcement Learning for Autonomous Vehicle Control in Dynamic Environments
Rohan Inamdar, Kavin Sundarr, Deepen Khandelwal, Varun Dev Sahu, Nitish Katal
View Paper
Conference · CVIP 2024
Embedding Swin Transformer with UNet for Segmentation of Urban Aerial Images
Kavin Sundarr, Rohan Inamdar, Varun Dev Sahu, Nitish Katal — 9th International CVIP Conference
View Paper
Conference · ADOP 2024 · Minsk, Belarus
Voice-Controlled Autonomous Agri-Robot for Organic Farming Pest and Disease Monitoring
Kavin Sundarr, Rohan Inamdar, Gopal U. Shinde — IV Int'l Conference on Agriculture Digitalization
View Paper
Patent · India #202441039698 · Published May 2024
A Surveillance System
K. Pradeep, K.P. Vijayakumar, K. Palani Thanaraj, Rohan Inamdar, S. Kavin Sundarr
View Patent
Patent · India #202441087748 · Published Nov 2024
A Robotic Hand for Automation of Tasks
Rohan Inamdar, S. Kavin Sundarr, Ajeyprasaath KB, Vetrivelan P, Krishna Kumba, Patri Upendar
View Patent
04

Projects

Robotics2024
VoiceBot — Autonomous TurtleBot3 Navigation
Full autonomous navigation system for TurtleBot3 Waffle with LiDAR and camera integration. Voice command interface with 100+ commands via ROS2 and Pocket Sphinx. 1.2s average response time across 5 map configurations using the Nav2 stack.
ROS2PythonNav2LiDARPocket Sphinx
Robotics · Voice AI · Navigation
Computer Vision2024
Semantic Segmentation — UNet + Swin Transformer
Hybrid model fusing UNet decoder with Swin Transformer encoder for satellite image segmentation. Outperforms DeepLab-v3+, UNet and SegNet on urban aerial benchmarks. Published at CVIP 2024.
PyTorchOpenCVSwin
NLP / LLM2024
Attention-Augmented BiLSTM Sentiment Analysis
Sentiment model using multi-head attention over BiLSTM layers. Outperforms standard LSTM and transformer baselines through enhanced contextual language modelling.
PyTorchNLPBiLSTM
Deep Learning2024
Deepfake Detection — GRU + CNN Ensemble
Real-time deepfake detection at 82% accuracy. Dedicated GRU model for video temporality combined with CNN image classifier. Trained across diverse multi-source datasets.
PyTorchGRUCNN
RL / Robotics2023
Deep Reinforced Robot — TD3 Navigation
TD3-based RL agent in ROS2 Gazebo 11 for autonomous obstacle avoidance. 82% navigation accuracy on goal-oriented tasks. Full training pipeline monitored with TensorBoard.
ROS2PyTorchTD3
Computer Vision2023
Lip Reading — 3D CNN + BiLSTM
Sentence-level lip reading web app using 3D-CNN and BiLSTM for real-time subtitle generation from visual lip movements. 97% accuracy. Deployed as a full Django web application.
TensorFlow3D-CNNDjango
05

Skills

Languages
Python
C / C++
SQL
MATLAB
R
Java
ML / AI Libraries
PyTorch
TensorFlow / Keras
OpenCV
YOLO
NumPy / Pandas
Matplotlib
Technologies & Tools
ROS / ROS2
Docker
Git / GitHub
Linux
Arduino / Hardware
SolidWorks
Let's BuildTogether.

Open to full-time roles in AI/ML Engineering, LLM systems, Data Analysis and Quantitative Research. Based in Manchester — open to remote and relocation.

Send a Message →