cv

An interactive CV, plus a formatted PDF view.

Basics

Name Partha Nath
Label 3D Vision-Language & Spatial AI
Email nath.partha@outlook.com
Phone +49 15239522871
Url https://parthanath.com
Summary

3D-vision engineer turned builder — I take frontier spatial-AI research and ship it to the people who need it.

  • Brought SpatialLM models to paying customers
  • Reverse-engineered SOTA training regimes
  • Worked across Assistive AI to Sovereign Tech
  • Led 2 startup ventures previously
  • Worked across several early-stage teams over the past 7 years

Key highlights

  • 🛡️ Now — Building in UK-EU Sovereign Tech (Stealth)
    Bringing 3D-perception and spatial-AI edge to UK-EU sovereign tech.
  • 🚀 Productised 3D VLM + Autoregressive Scene-Graph Generation
    Shipped generative 3D reconstruction to paying BIM/CAD drafters — frontier vision-language and autoregressive scene-graph models turned into a tool real users rely on built decisive customer feedback.
  • 📄 ADL4D — Published 4D Dataset
    Co-author of a 1.1M-frame 4D activity dataset (arXiv); designed its weakly-supervised hand-pose annotation pipeline.
  • 🏆 Kurt Fischer Prize
    TU Munich award for markerless multi-subject hand-tracking research.
  • 🚀 NVIDIA DGX Cloud Innovation Lab — Accepted
    Accepted into the NVIDIA DGX Cloud Innovation Lab; led the experiment design and team preparation.
  • 📚 Designed a TUM Course
    Co-created 'Project Lab: Human Activity Understanding,' now part of the TUM CIT curriculum.

Work

  • 2026.03 - Present
    Spatial AI & 3D Perception
    Stealth · UK-EU Sovereign Tech
    Applying 3D perception and spatial intelligence to problems in UK-EU sovereign tech.
  • 2024.12 - 2026.02
    Machine Learning Engineer
    Cirqular Pointcloud Analytics GmbH
    Took frontier 3D spatial-AI research to production for paying BIM drafters.
    • First to ship SpatialLM reconstruction to paying drafters
    • Reverse-engineered SOTA training stacks (Meta, HKU)
    • Trained 3D VLMs on 60+ GPU clusters for MVP ($150k GCP)
    • Handled R&D→MLOps
    • Product: Iterated directly with users and developers using the platform
  • 2023.09 - 2024.09
    System Engineer — Machine Learning & Computer Vision
    RevTec Systems AG · Casinos Austria International
    Real-time on-prem surveillance and analytics for casino tables.
    • Built and delivered a 3D tracking, analysis & fraud engine for UK & ZA casino chains
    • Massively reduced customer onboarding time and costs — from 2 weeks to <5 days
  • 2022.12 - 2023.05
    Co-Founder — Assistive Navigation (Dropout)
    SmartAIs (Unternehmer TUM)
    Founded an early-stage venture to help blind and low-vision people navigate independently — drove fundraising and poc validation, then dropped off to chase a different goal.
  • 2022.10 - 2023.05
    Software Engineering Intern
    Infineon Technologies AG
    Machine-vision software for 3D human pose on a depth camera.
    • 3D detection/tracking + multi-view calibration; sensor library for radar gesture training
  • 2021.06 - 2023.08
    Research & Teaching Assistant
    TUM Chair of Media Technology
    Markerless motion-capture research (Kurt Fischer Prize) and 3D-vision teaching.
    • Markerless motion capture research (Kurt Fischer Prize)
    • Co-designed and taught a TUM lab course for the CIT curriculum
    • Built a multi-camera capture studio
  • 2019.06 - 2020.03
    Founder
    Firefighting Drone Venture (SRM)
    Led a university venture bringing firefighting drones to South-East Asia — tackling operator load and training costs for scale.
    • Secured funding, equipment, and team (4 peers + 2 professors)
    • Built 3 MVPs; ran live tests and adversarial trials

Publications

Education

  • 2020.10 - 2023.09
    M.Sc.
    Technical University of Munich
    School of Computation, Information and Technology
    • Grade Total 1.6
    • Grade Thesis 1.0
    • Kurt-Fischer Prize
  • 2016.06 - 2020.05
    B.Tech.
    SRM Institute of Science & Technology
    Electronics & Communication Engineering
    • First Class with Distinction

Skills

3D Vision & VLMs
PointTransformerV3
Sonata
LLaMA 3.2
Qwen2
CLIP
SpatialLM
Deep Learning
PyTorch
DeepSpeed / ZeRO
HuggingFace
PyTorch3D
Detectron2
Pointcept
Production ML & Cloud
Multi-node training (60+ GPU)
GCP / AWS (A100, L40)
Docker
ClearML
3D Perception
Point-cloud algorithms
Multi-view geometry
Camera calibration
Object detection
Pose estimation
ICP
SLAM
EKF
Sensor Fusion
Programming & Tools
Python
C++
Javascript
Git
Claude Code
Leadership
Team management
Mentoring
Open-Source Datasets
ADL4D*
ScanNet++
Structured3D
H2O3D
DexYCB
Coco

Languages

English
Native
German
Conversational
Other (French, Hindi, Bengali)
Beginner / Conversational

Interests

Robotics
Perception stacks
Safe grasping & interaction
Navigation
Motion Capture
Marker & markerless
Monocular & multi-view
3D Scanning
Point/mesh reconstruction
Gaussian splatting
Scan2CAD
Drone / Autonomous Tracking
Sensor Fusion
EKFs
Object & area tracking
Ground stabilisation

References

Dr Rahul Gopal Chaudhari
TUM Senior Scientist
M.Sc. Marsil Zakour
TUM Doctoral Candidate
Maximilian Strobel
Infineon, System Architect — Machine Learning
Michael Winking
Infineon, Staff Engineer