Shubham Parab profile photo 1 on Tal

Shubham Parab

Robotics & Computer Vision Engineer | ROS 2 | MoveIt2 | SLAM | Robot Perception | AI | 3+ Years R&D Experience

United Kingdom

3+ years of work experience

Buckinghamshire New University
Mar 20264 mosJun 2026

High Wycombe

· Developed an innovative approach for 3D underwater scene reconstruction by integrating 3D Gaussian Splatting (3DGS) with a lightweight neural network to accurately model underwater light effects. · Reduced training time by over 90% compared to previous methods, enabling rapid model deployment. · Increased rendering speed to real-time performance (up to 241 FPS), making the solution ideal for autonomous underwater vehicles (AUVs) and real-time applications. · Addressed challenges such as light absorption, scattering, and colour distortion, resulting in higher-quality visual reconstructions. Applied advanced training techniques, including deferred activation and progressive parameter warm-up, to ensure stable and efficient learning. · Utilised Python, PyTorch, deep learning, and computer vision; validated improvements using the SeaThru-NeRF benchmark dataset.
Newcastle University
Mar 20263 mosMay 2026

Newcastle Upon Tyne

· Developed an end-to-end ML pipeline and interactive Streamlit dashboard for Tofa Ltd to automate LoRaWAN gateway site surveys, reducing manual planner workload by 97.5%. · Engineered an asynchronous scraping and geospatial viewpoint generation workflow (GeoPandas, Playwright) to automatically extract targeted Street View imagery. · Implemented a two-stage computer vision model using SAM3 for zero-shot object detection/cropping and a fine-tuned ConvNeXt CNN for suitability classification. · Achieved 98% accuracy and 99.2% precision on auto-approvals across 3,070 validation images. · Designed and integrated a human-in-the-loop, three-tier confidence policy (auto-approve, manual review, auto-reject) to ensure reliable, scalable network planning.
Lunaris Medical Ltd
Feb 20263 mosApr 2026

Newcastle Upon Tyne

• Automated the large-scale generation of 3D synthetic data using FLAME, generating 10,000+ annotated face meshes and drastically reducing manual dataset creation effort. • Executed mesh-level geometry processing with Python and NumPy, streamlining data handling. • Applied preprocessing techniques, including scaling, normalisation, and mesh simplification, to prepare data for model training • Evaluated and contrasted 3D landmark detection approaches to shape dataset design and boost model performance. • Engineered a scalable pipeline to batch-process 3D meshes and annotations efficiently.
Tata Consultancy Services
Jun 20223 yrs 3 mosAug 2025

Bengaluru

• Engineered end-to-end Computer Vision and Robotic Perception modules using Python and OpenCV for Retail Automation and Industrial Robotics. • Developed and deployed Object Detection and Anomaly Detection pipelines, enabling autonomous navigation and decision-making for omnidirectional robots. • Led the integration of Vision-ML models with ROS/ROS2 middleware and control systems, ensuring low-latency communication for real-time robotic manipulation. • Optimised data processing pipelines, achieving a 30% reduction in manual intervention and improved system accuracy during client demos.
Karthi wealth infotech limited
Jun 20212 mosJul 2021

Remote

• Architected scalable backend modules using Python and the Django Framework, ensuring high availability for web applications. • Implemented RESTful APIs and conducted systematic debugging to resolve legacy software issues, improving code maintainability and performance.

Shubham’s AI Stack

cursor
cursor
opencode
opencode
claudecode
claudecode

Education

Newcastle University

Msc in Data Science and AI, Artificial Intelligence

Newcastle University

20251 yr2026
Ramrao Adik Institute of Technology

Bachelor of Engineering - BE, Electrical and Electronics Engineering

Ramrao Adik Institute of Technology

20184 yrs2022

Join Shubham and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Shubham Parab on Tal

Headline

Robotics & Computer Vision Engineer | ROS 2 | MoveIt2 | SLAM | Robot Perception | AI | 3+ Years R&D Experience

About

Passionate about transforming the future through computer vision, robotics, and AI. With a proven track record of designing and implementing intelligent systems, I have successfully led projects leveraging machine learning algorithms and advanced imaging technologies. My expertise includes developing real-time image processing solutions that enhance automation and decision-making processes. I am dedicated to continuous learning and innovation in the tech landscape, aiming to create intelligent solutions that address real-world challenges.

Location

United Kingdom

AI stack

cursor

opencode

claudecode

Work experience

Research Assistant at Buckinghamshire New University, Mar 2026 - Jun 2026 · 4 mos, High Wycombe, · Developed an innovative approach for 3D underwater scene reconstruction by integrating 3D Gaussian Splatting (3DGS) with a lightweight neural network to accurately model underwater light effects. · Reduced training time by over 90% compared to previous methods, enabling rapid model deployment. · Increased rendering speed to real-time performance (up to 241 FPS), making the solution ideal for autonomous underwater vehicles (AUVs) and real-time applications. · Addressed challenges such as light absorption, scattering, and colour distortion, resulting in higher-quality visual reconstructions. Applied advanced training techniques, including deferred activation and progressive parameter warm-up, to ensure stable and efficient learning. · Utilised Python, PyTorch, deep learning, and computer vision; validated improvements using the SeaThru-NeRF benchmark dataset.

Research Intern – AI & Network Planning at Newcastle University, Mar 2026 - May 2026 · 3 mos, Newcastle Upon Tyne, · Developed an end-to-end ML pipeline and interactive Streamlit dashboard for Tofa Ltd to automate LoRaWAN gateway site surveys, reducing manual planner workload by 97.5%. · Engineered an asynchronous scraping and geospatial viewpoint generation workflow (GeoPandas, Playwright) to automatically extract targeted Street View imagery. · Implemented a two-stage computer vision model using SAM3 for zero-shot object detection/cropping and a fine-tuned ConvNeXt CNN for suitability classification. · Achieved 98% accuracy and 99.2% precision on auto-approvals across 3,070 validation images. · Designed and integrated a human-in-the-loop, three-tier confidence policy (auto-approve, manual review, auto-reject) to ensure reliable, scalable network planning.

Machine Learning Intern at Lunaris Medical Ltd, Feb 2026 - Apr 2026 · 3 mos, Newcastle Upon Tyne, • Automated the large-scale generation of 3D synthetic data using FLAME, generating 10,000+ annotated face meshes and drastically reducing manual dataset creation effort. • Executed mesh-level geometry processing with Python and NumPy, streamlining data handling. • Applied preprocessing techniques, including scaling, normalisation, and mesh simplification, to prepare data for model training • Evaluated and contrasted 3D landmark detection approaches to shape dataset design and boost model performance. • Engineered a scalable pipeline to batch-process 3D meshes and annotations efficiently.

System Engineer at Tata Consultancy Services, Jun 2022 - Aug 2025 · 3 yrs 3 mos, Bengaluru, • Engineered end-to-end Computer Vision and Robotic Perception modules using Python and OpenCV for Retail Automation and Industrial Robotics. • Developed and deployed Object Detection and Anomaly Detection pipelines, enabling autonomous navigation and decision-making for omnidirectional robots. • Led the integration of Vision-ML models with ROS/ROS2 middleware and control systems, ensuring low-latency communication for real-time robotic manipulation. • Optimised data processing pipelines, achieving a 30% reduction in manual intervention and improved system accuracy during client demos.

Django Developer at Karthi wealth infotech limited, Jun 2021 - Jul 2021 · 2 mos, Remote, • Architected scalable backend modules using Python and the Django Framework, ensuring high availability for web applications. • Implemented RESTful APIs and conducted systematic debugging to resolve legacy software issues, improving code maintainability and performance.

Education

Msc in Data Science and AI, Artificial Intelligence, Newcastle University

Bachelor of Engineering - BE, Electrical and Electronics Engineering, Ramrao Adik Institute of Technology