Logo
Andrei-Alexandru – Python, Snowflake, PyTorch, experts in Lemon.io

Andrei-Alexandru

From Romania (UTC+3)

flag
Data ScientistSenior
8 years of commercial experience
Administration
AI
Analytics
Automotive
Business intelligence
Cloud computing
Computer science
Data analytics
Machine learning
Manufacturing
Product management
AI software
Web development
Software development
Lemon.io stats

Andrei-Alexandru – Python, Snowflake, PyTorch

Andrei just wants to learn cool things and make the world a better place. As proof of his wishes, he has a PhD in Automation and Computer Science and experience in Data Science since 2018. Andrei is like a sponge; he absolves the knowledge and emits incredible results through hard work and curiosity.

Main technologies
Python
8 years
Snowflake
2 years
PyTorch
5 years
Additional skills
SQL
Microsoft Azure
Machine learning
AWS
Keras
Tensorflow
Microsoft Power BI
Ready to start
ASAP
Direct hire
Potentially possible
Ready to get matched with vetted developers fast?
Let’s get started today!

Experience Highlights

Head of AI & Analytics
May 2022 - Ongoing2 years 11 months
Project Overview

Industry leading analytics SaaS in Europe. Built the engineering team.

Skeleton
Skeleton
Skeleton
Responsibilities:

A custom OCR engine, a custom detector, an insanely fast and compute-light forecasting engine(statistical and neural forecasting) and future features (Python, PyTorch, GCP Vertex AI, AWS Lambda, SAM, AWS ECS, AWS Textract, Azure Document Studio, GCP Document AI, Azure ML, Azure OpenAI, Tesseract, YOLO, Transformer based models, CNN models, LLM models, MLOps, statistical forecasting, Deep learning forecasting, correlation analysis). Orchestrating ML workflows using Prefect ML Research (YOLO and leading OCR models) Data engineering(Prefect, MySQL, DynamoDB, Mongo, SES, AWS Batch, AWS Athena, AWS Glue, AWS RDS, Azure Storage, GCP Storage, Python, pandas, polars, deltalake, sql) and Data analysis(Microsoft PowerBI, Tableau, Excel, Sheets) Responsible for data integrity inside the StockRx platform: single source of truth for medication/pharmacy products Web development(SOLID, REST APIs, .Net, React, Recoil, Typescript/Javascript, AWS SQS, AWS Lambda, Dynamo DB, AWS API Gateway, observability (honeycomb) etc) DevOps(AWS, GCP, Docker, Gitlab workflows, Github actions, SAM, IaC(terraform, cdk, cloudformation), billing, architecture)

Project Tech stack:
AI
AWS
.NET Core
.NET
React
React Native
GitHub Actions
GPT
GitHub
API
API Gateway
AWS SES
AWS CloudFormation
AWS Lambda
AWS SageMaker
CI
CD
GCP
Azure DevOps
Azure SQL
Microsoft Azure
Python
Amazon CloudFront
Amazon Cognito
Amazon EC2
Amazon ECS
Amazon RDS
Amazon S3
Amazon SQS
Amazon SNS
GCP Compute Engine
Cloud Architecture
Cloud development
Product management
Product design
JavaScript
React Hooks
MySQL
Microsoft SQL Server
NoSQL
PostgreSQL
SQL
SQLAlchemy
Docker
Docker Compose
Airflow
AI researcher
May 2022 - Oct 20231 year 5 months
Project Overview

Research project to benchmark OCR models and trends. Evaluate models and benchmark price per page and supported mime types.

Skeleton
Skeleton
Skeleton
Responsibilities:

Led a research project focused on benchmarking state-of-the-art Optical Character Recognition (OCR) models and market solutions as of 2023.

Conducted a systematic evaluation of open-source and commercial OCR engines (e.g., Tesseract, EasyOCR, AWS Textract, Azure Form Recognizer, Google Document AI).

Designed benchmarking criteria including recognition accuracy, processing speed, supported MIME types (PDF, TIFF, PNG, DOCX), API capabilities, and real-world robustness.

Calculated and compared price-per-page metrics across providers to assess cost-efficiency for large-scale document processing pipelines.

Built automated test pipelines in Python to batch-process large datasets, collect model outputs, and generate comparative performance reports.

Analyzed OCR model trends (e.g., transformer-based OCR models, document layout analysis, handwriting recognition advances) and provided strategic recommendations for model adoption based on client needs and project constraints.

Delivered a comprehensive report summarizing technical findings, performance metrics, cost analysis, and future-readiness of OCR solutions.

Project Tech stack:
AI
SciPy
Python
NumPy
PyTorch
PyCharm
AWS
AWS SageMaker
Computer Vision
GCP
Microsoft Azure
JavaScript
Machine learning
Data Science
Data Modeling
Data analysis
Data visualization
GPT
LLM
Machine learning engineer
Jan 2022 - Jan 20231 year
Project Overview

Account healthscore is a project with the primary goal of delivering insights to the sales team about accounts. The machine learning model served predictions for each account, and then the resulting table was uploaded into Snowflake, connecting to a PowerBI dashboard. Everything was scheduled for a weekly run with the process running fully automated(tests included) at the end of the project.

Skeleton
Skeleton
Skeleton
Responsibilities:

Led the development of a cloud-based data processing and predictive modeling pipeline to deliver business insights to the sales team (account healthscore). Designed and implemented feature engineering workflows and machine learning models using Python and SQL, leveraging AWS services (EC2, Batch, ECS) and Snowflake as the data warehouse. Built automated scripts packaged in Docker containers and orchestrated through AWS Batch on ECS for scheduled weekly runs. Developed custom ETL processes (Airflow, dbt, python, seekwell, SQL, fivetran) to extract, transform, and load relevant datasets from Snowflake, performed advanced feature engineering, trained models offline, and generated actionable insights. Handled full automation and deployment, including configuring compute resources on AWS EC2 instances, monitoring job execution, and maintaining versioned deployments. Delivered consistent, high-quality outputs to business stakeholders, supporting data-driven sales strategies.

Project Tech stack:
PowerBI
Azure SQL
Microsoft Azure
SQL
PostgreSQL
SQLAlchemy
NoSQL
MongoDB
Microsoft SQL Server
Snowflake
AWS
AWS SageMaker
Amazon ECS
Amazon EC2
Python
JavaScript
AWS Lambda
Amazon S3
Amazon RDS
Data Science
Data Modeling
Data analysis
Data Warehouse
Data visualization
Business intelligence
Tableau
Database design
Big Data
Data mining
Data Security
Docker
Docker Compose
Machine learning consultant
Sep 2021 - Dec 20221 year 3 months
Project Overview

This research aims to make an experimental study on a standalone system to evaluate how various hardware configurations affect the overall performance of deep learning.

Skeleton
Skeleton
Skeleton
Responsibilities:

Main responsibilities:

  • Optimized running deep learning models with Fourier transform;
  • Optimized running deep NNs by performing lots of INT quantizations and lots of literature research;
  • Ran the slide algorithm and analyzed it with the benchmark;
  • Models analysis, pruning and ablation studies
  • Modified how deep learning models run on CPUs;
  • Analyzed the research results and showed that the performance greatly relies on the hardware configurations.
  • Integrations with MatLab
  • Process engineering
  • Lots of python and pytorch
  • Research paper written in Latex, rejected twice from ICML and NeurIPS
Project Tech stack:
AI
MATLAB
Python
PyTorch
React
JavaScript
Data analysis
Product management
AWS
Microsoft Azure
Machine learning lead and project manager
Feb 2021 - Dec 20221 year 10 months
Project Overview

Designed and led the development of a Visual Inspection Automation (VIA) system for real-time ceramic plate defect detection at one of Europe's largest ceramic manufacturers. Built a YOLO-based computer vision pipeline for detecting cracks, chips, and surface defects, achieving high precision and real-time inference speed. Led integration with industrial Fanuc robots for automated handling and rejection of defective plates, ensuring seamless operation within the production line. Managed data acquisition (industrial cameras), dataset creation, model training, optimization (precision, recall, mAP), and deployment under strict production constraints. Delivered a robust system that significantly improved defect detection rates and reduced manual inspection costs, contributing directly to operational efficiency gains.

Skeleton
Skeleton
Skeleton
Responsibilities:

Main responsibilities:

  • Created a deep learning model + industrial infrastructure that passed the pilot line;
  • Tested and customized an object detection model;
  • Created a robust data engine (version control with DVC & hosted on Azure);
  • Benchmarking of computer vision models, pytorch implementations
  • Created an active learning pipeline Integration with production servers and Siemens PLCs;
  • Started development for the Nvidia Jetson Xavier board;
  • Tried defect tracking in order to get rid of sensor integrations.
  • Product management and bulding a team of contractors and employees
Project Tech stack:
AWS
AI
Machine learning
React
JavaScript
Microsoft Azure
.NET
API
FastAPI
GCP
Computer Vision
Cloud Computing
Cloud Architecture
Clean Architecture
Product management
Automation engineer
Aug 2019 - Sep 20223 years 1 month
Project Overview

Working as a computer vision engineer in an industrial setting. Optimization of computer vision activities. Data science. Maintenance.

Skeleton
Skeleton
Skeleton
Responsibilities:

Developed and optimized computer vision models for defect detection, quality control, and visual inspection tasks in industrial production environments.

Applied deep learning techniques (CNNs, object detection, segmentation) and classical vision methods (OpenCV pipelines) to meet specific production requirements.

Performed model optimization for inference speed, resource constraints, and deployment on edge devices or industrial servers.

Conducted continuous maintenance for industrial hardware and software

Built data preprocessing pipelines for image cleaning, augmentation, annotation consistency, and labeling management.

Worked closely with cross-functional engineering teams (mechanical, automation, software) to align technical solutions with production workflows and business objectives.

Project Tech stack:
AI
Computer Vision
Python
Design system
Embedded Systems
Big Data
Algorithms and Data Structures
Data Security
Data analysis
Data mining
Data visualization
Data Structures
Data Science
Database design
Machine learning consultant
Aug 2021 - Feb 20226 months
Project Overview

Car license plate recognition is real-time detection and recognition of the license plates. The machine learning model of which is used for a smart parking solution. Used CRNN CTC, custom LSTMs and YOLO models. Also maintained a 3d labeling solution and benchmarked multiple labeling solutions. Versioning with dvc and git.

Skeleton
Skeleton
Skeleton
Responsibilities:

Main responsibilities:

  • Created a CRNN-CTC model that classified and detected license plate numbers/letters from 80x26p images;
  • Worked on car tracking algorithms with ScaledYOLOV4, DeepSORT and the clip model with zero-shot oriented tracking.
  • maintained a custom labeling solution and benchmarked off the shelf ones
  • custom LSTM for license plate recognition
  • lots of PyTorch
  • debugging and solving application issues
Project Tech stack:
AI
Azure DevOps
Azure SQL
Microsoft Azure
Machine learning
Product design
GitLab
GitHub
GitHub Actions
AWS
Cloud Computing
Cloud development
React
JavaScript
Python
PyTorch
Full stack engineer
Jan 2020 - Jan 20222 years
Project Overview

Simple document management platform for a SME client hosted on the cloud

Skeleton
Skeleton
Skeleton
Responsibilities:

Designed and implemented backend services using .NET Core for secure document upload, storage, retrieval

Developed a React-based frontend for user-friendly document management (upload, search, access control).

Architected and deployed the full solution on AWS, leveraging services like S3 (file storage), RDS (database), Cognito (authentication), and EC2/ECS (application hosting).

Containerized the application using Docker and orchestrated deployment through AWS ECS/AWS Lambda.

Designed and optimized relational database schema (AWS RDS) for efficient document metadata storage and querying. Dynamo DB for NoSQL document storage.

Implemented CI/CD pipelines

Ensured high availability, data durability, and security by applying AWS best practices (IAM policies, encrypted storage, HTTPS endpoints).

Conducted performance tuning and cost optimization of AWS infrastructure to match SME client requirements.

Provided technical documentation and support for client onboarding and system administration.

Project Tech stack:
React
React Hooks
React Native
.NET
.NET Core
JavaScript
AWS
Microsoft Azure
Docker
Git
CI
CD
Machine learning engineer
Jan 2020 - Nov 202010 months
Project Overview

Led the design and implementation of a computer vision-based Machine Learning PoC for detecting bearing defects in an automotive production line. Developed a custom dataset from high-resolution imaging, applied data augmentation techniques, and trained object detection models based on YOLO architecture (You Only Look Once). Handled end-to-end pipeline including dataset labeling, model training, hyperparameter tuning, performance evaluation (precision, recall, mAP), and deployment for real-time inference. Optimized the model for low-latency, high-accuracy defect detection under production constraints. Successfully validated the proof of concept, demonstrating significant improvements over manual inspection in both speed and defect identification rates.

Skeleton
Skeleton
Skeleton
Responsibilities:

Main responsibilities:

  • Built a deep learning model for the classification of images of bearings;
  • Mounted on top of an automotive component;
  • Built data engine with 99% accuracy for the inspections in the test environment (on more than 2 days of the test, about 1000 images);
  • Built a cheap solution with only about 2000 euros in funding.
  • Data streams and BI integration
Project Tech stack:
AWS
Python
RaspberryPi
FastAPI
JavaScript
Machine learning
Computer Vision
Microsoft Azure
Technical consultant
Nov 2019 - Mar 20204 months
Project Overview

Smart car project for parking spot reservations in an enclosed urban environment

Skeleton
Skeleton
Skeleton
Responsibilities:

Main activities: robot design support, PCB design support, planning support, implementing software ( Kalman filter, control algorithms, computer vision algorithms), IMU design support; [C, Keras, Raspberry Pi, Arduino, OpenCV, Matlab, Python, scipy, numpy, pandas, sklearn, Data labeling, Data pipelines]

Project Tech stack:
AI
NumPy
SciPy
PyTorch
Python
PyCharm
JavaScript
AWS
Microsoft Azure
Computer Vision
Automation engineer
Jul 2017 - Oct 20173 months
Project Overview

Built a computer vision model in order to dynamically assign tasks for an industrial robot based on what is on the production line

Skeleton
Skeleton
Skeleton
Responsibilities:

Designed and implemented a lightweight computer vision system to dynamically assign tasks to industrial robots based on real-time detection of objects on the production line.

Developed custom object detection pipelines using OpenCV and Haar cascade classifiers to recognize and differentiate production items with high-speed processing constraints.

Deployed the solution on Raspberry Pi hardware for affordable, distributed real-time inference directly on the production line.

Optimized image acquisition, preprocessing (thresholding, filtering, contour detection), and feature extraction techniques to handle varying lighting and part orientations.

Built communication interfaces between Raspberry Pi devices and industrial robots (e.g., Fanuc, ABB) to trigger task assignment based on detected objects.

Tuned classifier parameters and image processing workflows to minimize false positives and ensure reliable robot control.

Worked closely with automation and robotics teams to integrate the vision system into the existing production and control infrastructure.

Focused on achieving real-time performance within the hardware limitations of embedded systems without relying on GPU-accelerated deep learning.

Project Tech stack:
AI
Python
RaspberryPi
Data analysis
Data Modeling
Data Science
Data visualization
Data mining
Docker
Computer Vision
Cloud Computing

Education

2025
Automation and Computer Science
PhD

Languages

German
Advanced
Hungarian
Pre-intermediate
French
Pre-intermediate
Spanish
Pre-intermediate
Romanian
Advanced
English
Advanced

Hire Andrei-Alexandru or someone with similar qualifications in days
All developers are ready for interview and are are just waiting for your requestdream dev illustration
Copyright © 2025 lemon.io. All rights reserved.