Profilbild von Sven Badalyan KI ML LLM Entwickler Python GPT RAG Data Science Computer Vision OpenAI Deep Learning aus Berlin

Sven Badalyan

verfügbar

Letztes Update: 10.03.2024

KI ML LLM Entwickler Python GPT RAG Data Science Computer Vision OpenAI Deep Learning

Abschluss: Mathematik B.Sc. + M.Sc. (1.0), Physik B.Sc. an HU Berlin
Stunden-/Tagessatz: anzeigen
Sprachkenntnisse: deutsch (Muttersprache) | englisch (verhandlungssicher)

Dateianlagen

testo-project-portfolio_040423.gif
smart-aal-portfolio-compressed_040423.pdf
Referenzschrieben-Testo-Habisreutinger-Zalando_040423.pdf
alm-portfolio_040423.png
dayiana-portfolio_040423.png
CV-Sven-Badalyan-consulting_220623.pdf

Skills

Specialisations
Machine Learning, Cloud Computing, NLP, OpenAI, GPT4, OCR,
Neural Networks, Computer Vision, Image Processing, Embedded,
Time Series Analysis

Programming
Python > 11 years
C++ & C > 6 years
Matlab > 8 years
Azure > 3 years
AWS > 4 years

Software & Tools
Scikit-learn, OpenCV, Numpy, Tensorflow, PyTorch, PyTesseract, Docker, Pandas, SQL, Spark, AWS Sagemaker, Linux, CUDA, C++, Git, Power BI

IoT & Embedded
Jetson Nano, ARM Cortex, AT- mega

Production Code
Unittest, Pytest, Poetry

Projekthistorie

01/2023 - 12/2023
LLM/NLP Engineer
HeMaCare Medical GmbH (Pharma und Medizintechnik, 10-50 Mitarbeiter)

Project: Patient Data interaction with LLM

Development of an LLM language assistant on the iPad for daily medical practice.
• The language assistant summarily stores the spoken information in the patient's file.
• Development of OCR on iPad for converting a photo into text, storing it in the patient's file.
• Interaction with patient documents via LLMs and spoken language.
• Developed LLM finetuning pipeline via Langchain Framework.
• Fine-tuned non-proprietary LLM models for specific use cases
• Developed solutions via attention based metrics how much the LLM is hallucinating, getting LLMs with much less hallucination
• Integrated LLM use cases in a playground of the customer by integrating LLMs in a AWS Docker Endpoint and giving access via REST API
for the connection with the Frontend

05/2023 - 09/2023
Data Science Consultant
Microsoft (>10.000 Mitarbeiter)

Project: Deploy and optimize OpenAI services

Deploy and optimize OpenAI services for a big customer. Cloud migration in Azure and Azure Cognitive Services. Deploy GPT4, advanced prompt engineering, GPT4 fast API computation with vectorized embeddings using ML. Project ongoing.

Tech Stack: NLP, Azure Cloud, OpenAI, GPT4.0, Python, Prompt Engineering, Gitlab CI/CD, Azure DevOps.

11/2022 - 03/2023
Data Science embedded AI dev
Infineon Technologies AG intive GmbH (>10.000 Mitarbeiter)

Project: Smart Trunk Opener

As a Senior Data Scientist, I led the development of a Smart Trunk Opener project (joint project of infineon and intive), which aimed to accurately predict kick gestures for hands-free trunk opening using the BGT24***** radar based on the Doppler effect and using Neural Networks on embedded devices.
- Developed algorithms to detect abnormal signals and validate them as kicks using Python and Matlab
- Created NN models for better predictions, and optimised them using TensorRT for efficient use on embedded devices.
- Improved data reception and pre-processing on the radar using the C programming language.
- Compiled complete production code as C code using Atmel Studio and deployed it on the embedded system.

Tech Stack: Python, C++, C, Neural Networks, NumPy, Pandas, Pytest, Pytorch, Linux, Bash, Git, Matlab, Ifxdaq (Infineon Data Acquisition), Matplotlib, Time Series analysis, ARM Cortex, ARM Socket, RTOS, ATmega, Atmel Studio.

06/2022 - 01/2023
Computer Vision Software dev
Testo SE & Co. KGaA (1000-5000 Mitarbeiter)

Project: Bacteria Detection

Development of a bacteria detection project using microscopic images, achieving 99% accuracy in detecting the location and number of bacteria.
- Trained yolo5 deep neural networks to extract relevant bacteria bounding boxes using IoUs.
- Accelerated the AI on Jetson Nano by converting to TensorRT (CUDA) and developed the final C++ code interference with pre- and post-processors.
- Optimized the yolo network decoder from Python to C++ and programmed tensors directly on the GPU using CUDA C++.
- Reduced the AI utilizing Knowledge Distillation techniques to achieve high performance processing on the Jetson Nano.

Tech Stack: Python, C++, C, Neural Networks, Machine Learning, Object Detection, yolo, OpenCV, Pytest, Pytorch, CUDA, Numpy, Matplotlib, TensorRT, Git, Jupyter Notebook, OOP, Linux/Bash, AWS, Sagemaker, PyTest, Unittest, Jetson Nano.

06/2022 - 01/2023
Robotics Engineer
Gerhard Schubert GmbH (1000-5000 Mitarbeiter)

Project: Robot Manipulator Optimization

Determination of the optimal trajectory for the robot arm. I have developed a custom neural network to solve this optimization problem using physically modeled helper computations.
- Conducted research on optimal control problems via neural networks.
- Generated simulated data based on classical mechanics, performed data processing and normalization, and converted
   original Matlab files to Numpy.
- Constructed LSTM networks
- Enriched data with cubic splines and implemented objectoriented programming to produce productive and efficient
  code.

Tech Stack: Neural Networks (Recurrent Nets), Supervised Learning, Python, C++, Pytorch, Cuda, Numpy, Matplotlib, Torchdiffeq, MLFlow, Tensorboard, Autograd, Integrate, Torchsummary, Scipy, Torchcubicspline, Git, Jupyter Notebook, OOP, Pytest.

01/2022 - 06/2022
Computer Vision Specialist
DAYIANA GmbH (50-250 Mitarbeiter)

Project: Breast Cancer Detection on MRI

Development of a neural network-based algorithm to detect, classify and segment breast tumors in mammography X-ray images to improve radiologists' performance in breast cancer screening.
- Used segmentation techniques to train Mask R-CNNs to detect the tumors.
- Improving the inferenc via pretraining of the Mask R-CNN with the bounding box mask of the Yolo detector. Then
  training on qualitatively better but few masked data.
- Integrated sensitivity and precision metrics, and achieved stateof- the-art results.
- Deployed the finished code on AWS endpoint for professional level breast cancer detection.

Tech Stack: Python, C++, Mask RCNN, Segmentation Networks, PyTorch, NumPy, Machine Learning, OpenCV, AWS, Pandas, Git, Jupyter Notebook, Unittest.

05/2020 - 11/2021
Data Science Expert
Smart AAL GmbH (10-50 Mitarbeiter)

Project: Fall Detection

Development of Fall detection Machine Learning Algorithms for a Smart Vision Assistant.
- Collect data of human skeleton in various fall scenarios via motion capture and skeleton detection algorithms.
- Balance the dataset with fall and non-fall scenarios to ensure that the machine learning algorithm can distinguish between normal and abnormal movements.
- Feature Extraction: relevant features extracted from skeleton data to represent the movement patterns: joint angles, joint velocities, and acceleration
- Data saved on AWS S3 bucket.
- Extracted features used to create matrices which were fed into a machine learning algorithm.
- Used AWS AutoML to find best ML model.

Tech Stack: Python, Scikit-learn, OpenCV, Pytorch, Image-Pose, AWS, Sagemaker, AutoML, AutoPilot, Cuda, Linux, Git, Pytest.

Project: Voice ReID, Voice to Text

Development of speech recognition system that can identify the speaker and transcribe the language from audio data.
- Audio data divided into 4-second segments sampled at 16kHz.
- Feature extraction techniques on audio data, such as MFCCs, Mel-scale spectrogram, chromagram, spectral contrast, and tonnetz, based on STFT, utilizing Kaldi.
- Utilizing Scikit-learn for feature clustering.
- Utilizing FFT (Fast Fourier Transformation) for denoising and feature extraction.
- Creation of VoiceReID custom model via PyTorch and TensorFlow.
- NLP algorithms for speech-to-text transcription, utilizing part-of-speech tagging and word sense disambiguation.
- Utilizing Gensim and NLTK for text summarization, tokenization, stemming, lemmatization, part-of-speech tagging, parsing
- Applied named entity recognition to identify named entities in text data and categorize them into predefined classes

Tech Stack: Python, pyannote, Kaldi, NLP, AWS Sagemaker, EC2, S3, Lambda, NumPy, TensorFlow, LSTM, Scikit-learn, NLTK, Spacy, Gensim, CoreNLP, Transformers, Hugging Face, Pandas, SQL, FastAPI, Git, Bash, VS Code, Unittest, Poetry.

01/2020 - 05/2020
Robotics Engineer
Zalando SE (>10.000 Mitarbeiter)

Project: Box Optimization
Minimizing the amount of empty space in packages. This reduced not only CO2 emissions but also transport costs. My solution achieved a 10% improvement in packing efficiency.
- Utilized data sampling, dimensionality reduction and data approximation techniques to reduce the data size.
- Modelled the packages as matrices to rotate and modify easily via numpy.
- Developed evolutionary algorithms with efficient mutation and breeding methods as tensor operations on CUDA to
   have very fast parallel breedings.
- Benchmarked the results using MILP optimiser.

Tech Stack: Python, Numpy, Torch, Cuda C++, Pandas, SQL, Pytorch, Cuda, Cudnn, AWS, Sagemaker, Docker, Git, Jupyter Notebook, OOP, Clustering, NP-hard problems.

01/2019 - 12/2019
OCR Vision Specialist
Franz Habisreutinger GmbH & Co. KG (500-1000 Mitarbeiter)

Project: Invoice Recognition, OCR
Development of an OCR for invoice recognition software that checks for invoice errors.
- Built an efficient SQL command search function to simplify the work.
- Used OpenCV to apply image recognition techniques.
- Implemented deep learning techniques for text recognition on invoices.
- Developed deep auto-encoders for data dimension reduction and noise reduction.
- Used Convolutional Neural Networks to improve logo recognition.

Tech Stack: Machine Learning, NLP, Python, Tensorflow, Numpy BigData, PyTesseract, Git, Bash, AWS, VPN, SQL.

Zertifikate

Azure AI Fundamentals
2023
Azure AI Engineer Associate
2023

Reisebereitschaft

Weltweit verfügbar
  • Reisebereitschaft Europaweit

Bewertungen

CEO (Andreas Mazat)
"Hereby I confirm that Mr. Badalyan was involved in my company as a Data Science Consultant.
Hereby I want to mention Mr. Bada Badalyans working qualities:
- disciplined, - competent, - reliable,
- creative,
- hard-working,
- obliging,
- stress resistant."
CTO (Markus Münzer)
"Wir sind als Kunde von Herrn Badalyans Leistungen überzeugt. Seine agile und kreative Arbeitsweise hat Stück für Stück dafür gesorgt.
Seine Fachkenntnisse waren für das Projekt von großem Nutzen. Zu den Kenntnissen und Stärken gehören der Umgang mit KI-basierten Anwendungen, Python und Einbettung von Lösungen in eine skalierbare IoT-Umgebung. Neben seinen technischen Fähigkeiten möchten wir die starken Kommunikationsfähigkeiten und seine sehr anschaulichen Ergebnisstörstellungen betonen."
Senior Project Manager (Bernhard Lerchner)
"Deine Herangehensweise an die übertragenen Aufgaben war sehr strukturiert, kreativ/innovativ und gut vorbereitet. Der Umgang und die Kommunikation mit Kollegen bzw. dem Kunden, sowie deine Hilfsbereitschaft waren vorbildlich. Du bist motiviert bei der Sache, hast einen sehr guten technischen Wissensstand und du zeigst Eigeninitiative."

exali IT-Haftpflicht-Siegel (Sondertarif für Freelancermap-Mitglieder)

Das original exali IT-Haftpflicht-Siegel bestätigt dem Auftraggeber, dass die betreffende Person oder Firma eine aktuell gültige branchenspezifische Berufs- bzw. Betriebshaftpflichtversicherung abgeschlossen hat. Diese Versicherung wurde zum Sondertarif für Freelancermap-Mitglieder abgeschlossen.

Versicherungsbeginn:
10.03.2023

Versicherungsende:
01.04.2024

Profilbild von Sven Badalyan KI ML LLM Entwickler Python GPT RAG Data Science Computer Vision OpenAI Deep Learning aus Berlin KI ML LLM Entwickler Python GPT RAG Data Science Computer Vision OpenAI Deep Learning
Registrieren