Kanishk
Navale

Stuttgart 🇩🇪
Fine Arts Machine Design Robotics Math Optimization Machine Learning Reinforcement Learning Deep Neural Networks Computer Vision High-Dimensional Data Analysis Natural Language Processing AI Agents
// Projects scroll →
Der Föhnwind
Der Föhnwind
Fine Arts
Kunstsammlung
Delta Robot
Delta Robot
Motion Control
TRIS-1A
Robot Physics Engine
Robot Physics Engine
Constrained Optimization
Physics Engine
AI for Robot Tasks
AI for Robot Tasks
Deep Reinforcement Learning
AI for Robot Tasks
SLOG
Single Label Object Grasping
Object-Aware Robot Control
SLOG
// Career Odyssey ↓ scroll
Greenbone AG.
AI Engineer
05.2024 – Present · Stuttgart, Germany
Engineering secure AI-agents and intelligent vulnerability management systems, pushing the boundary of what autonomous security tooling can do.
Sereact GmbH.
Senior Deep Learning Engineer
11.2022 – 01.2024 · Stuttgart, Germany
Led the design & development of a vision-based LLM for robots. Initially, fine-tuned a foundation model with LoRA. Later, integrated it with a 'Point Transformer-2' architecture using modified geodesic multi-head self-attention for enhanced robot & object interaction boosting number of pick & place operations.
Sereact GmbH.
Master Thesis Student
05.2022 – 11.2022 · Stuttgart, Germany
Developed an end-to-end deep learning model that regresses the generalised object representations as visual dense descriptors (embeddings) while additionally regressing object pose invariant 3D keypoints. The DNN was optimised using self-supervised geometry aware loss functions, eliminating the need for manual annotated labels. The master thesis was awarded a '1.3' which is an excellent grade.
Bosch Center for AI
Intern — Reinforcement Learning & Planning
11.2021 – 04.2022 · Renningen, Germany
Implemented oriented bounding-box pruning & grouping for visual object pose registration using a DNN regressed feature space. The DNN feature space was optimized on the pixelwise distributional loss & agglomerative hierarchical clustering.
Max Planck Institute
Work Student — Research Assistant
04.2021 – 10.2021 · Stuttgart, Germany
Integrated a robot physics engine from scratch, introducing hybrid motion force control to the NYU-Finger robot (a leg of a quadruped robot) with the in-house fabricated capacitive haptic sensor with robust real-time state estimation.
FANUC India Pvt. Ltd.
Robot System Engineer
06.2016 – 08.2018 · Bangalore, India
Commissioned 48 industrial robots, 2D/3D vision, machine tending & IoT systems as part of the design & site deployment team. The technical & commercial proposals pitched generated revenues more than the set yearly target.
// About

Started with pencils, not keyboards. Before any line of code, I was sketching mechanisms, trying to understand how things move and why. That instinct led me into robotics, then into deep learning, and now into AI agents that operate autonomously in high-stakes security environments.

I've worked across the full stack of intelligent systems from commissioning 48 industrial robots on factory floors, to building montion control systems from scratch, to fine-tuning foundation models for robotic manipulation. I don't just apply methods; I reach for the right tool & build it if it doesn't exist.

What drives me is the belief that the most interesting problems sit at the boundary where perception meets action, where autonomy meets safety, where art meets engineering. That's where I work best.

0yr
Work Experience
0+
Open Source Projects
0
Research Publication
// School Compass scroll →
M.Sc. Computer Science
Universität Stuttgart 🇩🇪
10.2019 – 10.2022
Designed information maximization variation encoder (Info-VAE) for high data dimensional analysis & decomposition to its latent state, securing top-2 in the class.
B.E. Automation & Robotics
BVBCET 🇮🇳
06.2012 – 06.2016
Led student team of size 10 to participate in ABU-Robocon international event engineering 2 badminton playing robot. Furthermore, built a delta-style parallel robot for the bachelor's graduation project.