Lasse Hyyrynen, Developer in Helsinki, Finland
Lasse is available for hire
Hire Lasse

Lasse Hyyrynen

Verified Expert  in Engineering

Bio

Lasse is a data scientist with a background in mathematics. He excels in Natural Language Processing (NLP), data modeling, machine learning, Python, and artificial intelligence projects. He works on real-world problems that explore the extensive possibilities of ML and AI. Lasse has developed ML models that detect cybersecurity threats, created processing pipelines for machine learning models, and improved speech recognition accuracy by enhancing the pronunciation model for foreign words.

Portfolio

F-Secure
Python 3, PySpark, PyTorch, Amazon Elastic MapReduce (EMR), AWS Lambda...
Utopia Analytics
Python 3, Scikit-learn, PyTorch, Generative Pre-trained Transformers (GPT)...
Lingsoft
Python 3, Kaldi, SQL, RabbitMQ, Scikit-learn...

Experience

Linux - 20 yearsMachine Learning - 7 yearsDeep Learning - 7 yearsScikit-learn - 5 yearsPyTorch - 3 yearsBokeh - 3 yearsPySpark - 2 yearsRabbitMQ - 1 year

Availability

Part-time

Preferred Environment

Linux, PyCharm, Slack

The most amazing...

...product I've created is the "JF" JSON and YAML query tool for performing complex transformations on datasets.

Work Experience

Data Scientist

2019 - 2021
F-Secure
  • Developed machine learning models to detect cyber security threats.
  • Built tools to integrate machine learning to various services.
  • Developed the company MLOps practices to provide top quality AI services.
Technologies: Python 3, PySpark, PyTorch, Amazon Elastic MapReduce (EMR), AWS Lambda, AWS Batch, Apache Spark, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Machine Learning, PyCharm, Python, Linux, Docker, Bokeh, Visualization Tools, Indexing, Asyncio, Pandas, SciPy, NumPy, TensorFlow, Jupyter, Data Analysis, Clustering, Data Visualization, Matplotlib, Deep Learning, SQL, GitLab CI/CD, Data Science, Decision Tree Regression, Decision Tree Classification, Data Engineering, Spark ML, Spark

Text Data Scientist

2017 - 2019
Utopia Analytics
  • Developed classifiers to various discussion forums and market places to automate human moderator work.
  • Researched deep learning models to enhance classification results.
  • Monitored model quality and built automation to retrain the model using the latest data.
Technologies: Python 3, Scikit-learn, PyTorch, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Machine Learning, PyCharm, Python, Linux, Docker, Bokeh, Visualization Tools, Indexing, Pandas, SciPy, NumPy, TensorFlow, Jupyter, Data Analysis, Clustering, Data Visualization, Matplotlib, RabbitMQ, Deep Learning, SQL, GitLab CI/CD, Data Science, Decision Tree Regression, Decision Tree Classification, Data Engineering, Apache Kafka

Software Architect

2011 - 2017
Lingsoft
  • Developed a scalable processing pipeline for machine learning models.
  • Improved speech recognition accuracy by enhancing the pronunciation model for foreign words.
  • Developed and enhanced multiple algorithms for specific NLP tasks.
  • Managed multiple projects to meet customer requirements.
Technologies: Python 3, Kaldi, SQL, RabbitMQ, Scikit-learn, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Machine Learning, PyCharm, Python, Linux, Bokeh, Visualization Tools, Session Initiation Protocol (SIP), Indexing, Asyncio, Pandas, SciPy, NumPy, Speech to Text, TensorFlow, Jupyter, Data Analysis, Clustering, Data Visualization, Matplotlib, Deep Learning, GitLab CI/CD, Data Science, Data Engineering

JF Dataset Filtering Tool

https://github.com/alhoo/jf
A tool for filtering, converting, and transforming datasets from format to format. The tool is a partial clone of the popular jq-tool, but it is written by data scientists for data scientists on Python. The aim of the tool is to make data conversions simpler and reusable in Python scripts and projects.
2006 - 2012

Master's Degree in Mathematics and Computer Science

Aalto University - Espoo, Finland

Libraries/APIs

Scikit-learn, Pandas, PyTorch, PySpark, SciPy, NumPy, Matplotlib, Asyncio, TensorFlow, Spark ML, Luigi

Tools

PyCharm, Jupyter, GitLab CI/CD, Slack, Kaldi, RabbitMQ, Amazon Elastic MapReduce (EMR), AWS Batch, Whisper

Languages

Python 3, Python, SQL, C++

Platforms

Linux, Docker, AWS Lambda, Apache Kafka

Frameworks

Spark, Apache Spark

Storage

MongoDB, PostgreSQL, Azkaban

Other

Machine Learning, Data Science, Deep Learning, Speech to Text, Bokeh, Session Initiation Protocol (SIP), Indexing, Natural Language Processing (NLP), Visualization Tools, Clustering, Data Visualization, Data Engineering, Decision Tree Classification, Generative Pre-trained Transformers (GPT), Data Analysis, Decision Tree Regression, Predictive Modeling, Time Series Analysis

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