Petar Nikolov, Developer in Sofia, Bulgaria
Petar is available for hire
Hire Petar

Petar Nikolov

Verified Expert  in Engineering

Bio

Petar is a senior machine learning engineer with 11+ years of experience in computer vision and audio analysis. He has a professional programming background with C++, Python, and C#. He has developed from scratch and pushed projects to production for large companies and startups. Petar's works include building an app for face analysis and correction, developing NLP microservices for automation, and creating a personal assistant for home security and automation.

Portfolio

Beauty Labs
Python, TensorFlow, Computer Vision, Audio Analysis, Computer Vision Algorithms...
Resolve Systems
Python, C#, Microservices, RabbitMQ, PostgreSQL...

Experience

  • Git - 11 years
  • OpenCV - 11 years
  • Computer Vision - 11 years
  • Python 3 - 6 years
  • Microservices - 5 years
  • Audio Analysis - 5 years
  • Deep Learning - 5 years
  • TensorFlow - 5 years

Availability

Part-time

Preferred Environment

Windows, Python 3, TensorFlow

The most amazing...

...thing I've developed is a personal assistant for home security and automation capable of understanding voice commands and recognizing faces.

Work Experience

Machine Learning Engineer

2020 - 2023
Beauty Labs
  • Built an app that scans a face and generates an "issue report" with all the detected wrinkles and their depth, moles, acne, and other blemishes.
  • Developed a face-correction app that shows how good a face can look if all the detected issues are gone.
  • Created an iOS app capable of detecting the exact millisecond of a song being played from a list of pre-trained songs.
Technologies: Python, TensorFlow, Computer Vision, Audio Analysis, Computer Vision Algorithms, PyTorch, Natural Language Processing (NLP), Convolutional Neural Networks (CNNs), Artificial Intelligence (AI), API Integration, Machine Learning

Machine Learning Engineer

2017 - 2020
Resolve Systems
  • Developed an NLP microservice that supports the "automation builder tool," an essential project for the company.
  • Managed the machine learning team's day-to-day tasks.
  • Oversaw the entire machine learning pipeline and its integration into the main product.
Technologies: Python, C#, Microservices, RabbitMQ, PostgreSQL, Natural Language Processing (NLP), Data Science, Artificial Intelligence (AI), Machine Learning

Experience

Audio Tracker

An application that extracts song fingerprints. It can accurately identify the precise timestamp and song title among thousands of predefined songs. The algorithm is stable even in noisy environments.

Face Analytics

A healthcare app that scans and detects facial blemishes to generate better suggestions for skin treatment. The customer can use their webcam to take a photo of their face. The photo is then processed through machine-learning microservices running image processing algorithms and deep-learning models to extract information about the customer's wrinkles, skin sensitivity, and other blemishes, calculating the overall beauty score.

Reflection Removal

Using a camera placed on an oven's handle, the algorithm reduces or eliminates the reflections caused by the oven's multi-layered glass. Without this algorithm, it is impossible to see what is inside.

Skin Dirt Particles Detection

An algorithm that uses various color spaces and image processing techniques. The project aimed to identify all dirt particles on the skin using a microscope and compare the results before and after washing.

Object Detection from Aerial Photos

A software providing analytics for insurance companies. It can detect and understand different hazards in a customer's property, such as pools and trampolines, from aerial images. The algorithm can also analyze roof conditions.

Education

2011 - 2013

Master's Degree in Computer Science

Technical University of Sofia - Sofia, Bulgaria

2011 - 2013

Master's Degree in Telecommunications

Technical University of Sofia - Sofia, Bulgaria

Skills

Libraries/APIs

TensorFlow, Keras, NumPy, OpenCV, PyTorch

Tools

RabbitMQ, Git, Jira, Visual Studio

Languages

Python 3, C#, Python, C++

Paradigms

Microservices, Socket Programming, Object-oriented Programming (OOP), Design Patterns

Platforms

Windows, Linux

Storage

PostgreSQL

Other

Computer Vision, Deep Learning, Audio Analysis, Image Processing, Computer Vision Algorithms, Convolutional Neural Networks (CNNs), Artificial Intelligence (AI), API Integration, Machine Learning, Natural Language Processing (NLP), Data Science, Networks, Network Protocols, Data Encryption, Medical Imaging

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring