Experience
Edge AI Software Engineer
Neura Robotics GmbH
- Deployed and optimized Vision-Language-Action (VLA) and diffusion policy models on NVIDIA Jetson Orin and Jetson Thor, meeting real-time inference latency targets for humanoid robot control loops.
- Built TensorRT engine pipelines (PyTorch → ONNX → TensorRT) with INT8/FP8 post-training quantization, calibration dataset design, and quantization-aware validation, reducing inference memory footprint by over 3× on Jetson without accuracy regression.
- Developed custom CUDA C++ plugins and CUDA Graphs for latency-deterministic, real-time policy execution – meeting hard runtime and memory constraints on embedded GPU targets.
- Developed an inference engine for VLA models on top of llama.cpp bringing different VLA policies under single runtime, packaging each as a single self-contained GGUF that needs no Python or PyTorch.
- Profiled and tuned GPU execution using NVIDIA Nsight Systems and Nsight Compute, identifying CUDA kernel bottlenecks, memory bandwidth saturation, and SM occupancy issues across Jetson Orin and Thor compute profiles for cross-layer performance optimization.
Embedded AI Software Engineer
Huber Automotive AG
- Architected and benchmarked embedded AI inference pipelines on the NXP S32V234 vision processor and constrained microcontroller targets, evaluating optimization strategies for real-time on-device perception under strict power and memory envelopes with no GPU acceleration.
- Developed quantized (INT8) human and object detection models for embedded deployment, applying structured sparsity and token pruning to transformer-based detectors to meet hard compute and memory limits on microcontroller-class hardware.
- Developed embedded AI applications for intelligent battery management (ESP32, Infineon AURIX™ TC3xx/TC4xx) for SOC/SOH estimation, requiring hardware/software co-design across constrained microcontroller targets.
- Built multi-modal sensor fusion pipelines (camera, radar) in C++ and Python with ROS2 for autonomous mobility and target-tracking on embedded platforms.
- Contributed to the VeoPipe project with Fraunhofer IPA, building a certifiable, reproducible MLOps pipeline with standardized testing and traceability for embedded robotics deployment across diverse accelerator targets.
AI Research Intern
Reliev
- Conducted an extensive literature review on multimodal biosignal analysis and deep learning architectures for seizure and motion detection.
- Designed and trained deep learning models for biosignal and motion pattern recognition using CNNs and RNNs on ECG and IMU data.
- Built end-to-end data ingestion and preprocessing pipelines (FastAPI, InfluxDB) for signal fusion, noise filtering, and active learning.
Data and Automation Engineer
EMIS Health
- Developed Machine Learning models to analyze speech input of emergency calls for NHS, United Kingdom.
- Worked on design and development of DataLake on Starburst and AWS with Big Data technologies such as Apache Spark, Kafka, and Airflow, Presto and also databases such as SQL Server, Postgres, Presto, and DynamoDB.
- Developed and implemented QA automation tests utilizing FlaUI, xUnit, Specflow, and Cucumber with C# for .NET applications
Associate Software Engineer
Accenture
- Conducted analysis of large-scale telecommunications data utilizing Data Warehousing and ETL techniques.
- Created automation frameworks using Python and Selenium to increase testing efficiency and accuracy.
- Experience with various tools such as Splunk, Tableau, etc., for data visualization and analysis purposes.
Industry experience
See where this freelancer has spent most of their professional time.
Experienced in Healthcare, Manufacturing, Automotive, Information Technology, Biotechnology, and Telecommunication.
Business area experience
See which departments and functions this freelancer has contributed to most.
Experienced in Information Technology, Research and Development, Quality Assurance, Product Development, and Business Intelligence.
Frequently asked questions
Have questions? Find more information here.
Adithya is based in Munich, Germany and can operate in on-site, hybrid, and remote work models.
Adithya speaks the following languages: English (Native), French (Intermediate), German (Elementary).
Adithya has at least 8 years of experience. During this time, Adithya has worked in at least 5 different roles and for 5 different companies. The average length of individual experience is 2 years and 6 months. Note that Adithya may not have shared all experience and actually has more experience.
Based on recent experience, Adithya would be well-suited for roles such as: Edge AI Software Engineer, Embedded AI Software Engineer, AI Research Intern.
Adithya's most recent position is Edge AI Software Engineer at Neura Robotics GmbH.
In recent years, Adithya has worked for Neura Robotics GmbH, Huber Automotive AG, and Reliev.
Adithya is most experienced in industries like Healthcare, Manufacturing, and Information Technology. Adithya also has some experience in Automotive, Telecommunication, and Biotechnology.
Adithya is most experienced in business areas like Information Technology, Research and Development, and Quality Assurance. Adithya also has some experience in Product Development and Business Intelligence.
Adithya has recently worked in industries like Manufacturing, Automotive, and Biotechnology.
Adithya has recently worked in business areas like Information Technology, Product Development, and Research and Development.
Adithya holds a Master in Control and Robotics - Advanced Robotics from Ecole centrale de Nantes and a Bachelor in Automotive Engineering from Anna University.
Adithya is immediately available part-time for suitable projects.
Daily rate distribution
The rates shown represent the typical market range for freelancers in this position based on recent contracts on our platform.
Average rates for similar positions
Rates are based on recent contracts and do not include FRATCH margin.
The average daily rate is the mean of all daily rates from recent contracts of comparable freelancers on our platform.
The median daily rate is the middle value of all daily rates — half of comparable freelancers charge less, half charge more. Unlike the average, it is barely affected by outliers.
Calculated based on our freelancers’ daily rates as of 19 Nov 2026. Actual rates may vary depending on seniority level, experience, skill specialization, project complexity, and engagement length.
Similar freelancers
Discover other experts with similar qualifications and experience
Peter S.
Last position:
Senior ML Engineer & AI Researcher at Anonymous Client
Project: Defect Generation on Test-Bench Images of Metal Surfaces Environment: Automated Visual Inspection (AVI), Metallurgy & Manufacturing
- Objective & Implementation: Designed, architected, and trained Generative Adversarial Networks (Pix2PixHD / SPADE) for image-to-image transformation. Targeted generation of synthetic material defects (e.g., cracks, inclusions, scale) on rough metal surfaces under real test-bench lighting conditions for privacy-compliant and efficient dataset expansion (data augmentation).
- Technical Design: Implemented robust Generative AI and computer vision pipelines in Python and PyTorch. Used semantic segmentation approaches for mask-controlled defect synthesis and subsequent evaluation with EfficientDet object detection models.
- Business Impact: Massive dataset upscaling (10x) without time-consuming and costly physical test-bench runs, while significantly improving the detection performance of automated inspection systems.
Technologies & Skills Used: Python | PyTorch | SPADE | Pix2PixHD | EfficientDet | Machine Learning | Semantic Segmentation | Computer Vision
Kai W.
Last position:
biobedded systems GmbH
- Embedded software development for EMS safety boards in medical technology according to IEC 62304 / ISO 13485
- Technologies: C++, OpenCV, Python, Qt6, JTAG, UART, CMake, IEC 62304, ISO 13485
Jürgen F.
Last position:
AR/VR/XR Architect at Deutsche Telekom
- Defined a generic, universal system platform for XR (AR, VR) use cases as part of the European IPCEI initiative
- Evaluated available options for backend, streaming and client implementations
- Developed PoC implementations and conducted technical evaluations of potential components
- Led the development team and defined the target system architecture for a complete end-to-end solution
- Designed and integrated GenAI PoCs (LLM, time series, prediction, agents)
- Researched NeRFs and Gaussian Splatting for XR content creation and analyzed methods to measure and reduce system latency
- Worked on GPU scheduling, CUDA and related topics
- Defined and implemented back-office and end-user dashboards using Grafana and Superset
- Used Jaeger tracing to analyze specific events
- Defined a GenAI-based automatic alerting feature for specific events and event clusters with KPI values
- Integrated AR/VR/XR IoT devices
- Collaborated with business development and UX teams in a parallel design thinking track to align technical scope with customer journeys
- Integrated the new services and platform into existing telco environments and analyzed tools like Camara for partial integration and handover scenarios
Nenad B.
Last position:
Safety Video Analytics Project for Airbus at Airbus
- Developed a real-time video analytics proof-of-concept for deployment on NVIDIA Jetson edge devices.
- Implemented DeepStream pipelines including object detection, tracking, human pose estimation, face anonymization, and zone intrusion detection.
- Built a Qt/Python demonstration UI interfacing with the AI pipeline via REST APIs.
Hans G.
Last position:
Deal with Green AR
- Development of an e-learning platform as an app for Android and iOS
- Use of Unity to promote environmentally conscious interaction with nature for teachers and students
Arne H.
Last position:
Embedded Fullstack Developer at IoT / Infrastructure Automation Sector
- Analysis of legacy codebase and identification of architectural issues, implementing improvements in coordination with the Product Owner.
- Development of clean, efficient, and fully documented code following established software engineering practices and standards.
- Analysis of Erlang components in backend and device layers to provide recommendations for ensuring stable system operation.
- Setup and optimization of CI/CD pipelines on client infrastructure, including testing, debugging, and certificate management quality assurance.
- Participation in planning, design, and implementation of epics and stories according to Product Owner specifications.
- Technical consultation for Product Owner regarding Erlang codebase management and best practices.
- Collaboration with Product Owner, Scrum Master, and development team to ensure timely delivery of features.
- Elixir & Phoenix + PostgreSQL
- Erlang
- IoT
- CI/CD
- Git
- Agile/Scrum
- Docker
- Kubernetes
- Frontend (VueJS)
- Embedded Devices
Experts recently working on similar projects
Freelancers with hands-on experience in comparable project as a Edge AI Software Engineer
Nearby freelancers
Professionals working in or nearby Munich, Germany
