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

Lasse Hyyrynen

Verified Expert  in Engineering

Data Scientist and Developer

Location
Helsinki, Finland
Toptal Member Since
March 18, 2021

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.

Machine LearningLinuxPython 3PythonNatural Language Processing (NLP)Deep LearningData VisualizationData EngineeringBokehClusteringSQLSciPyNumPyJupyterPandas

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), GPT...
Lingsoft
Python 3, Kaldi, SQL, RabbitMQ, Scikit-learn...

Experience

Linux - 20 yearsMachine Learning - 7 yearsDeep Learning - 7 yearsScikit-learn - 5 yearsBokeh - 3 yearsPyTorch - 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, GPT, 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), GPT, 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), GPT, Natural Language Processing (NLP), Machine Learning, PyCharm, Python, Linux, Bokeh, Visualization Tools, SIP Protocol, 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.

Languages

Python 3, Python, SQL, C++

Libraries/APIs

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

Paradigms

Data Science

Platforms

Linux, Docker, AWS Lambda, Apache Kafka

Other

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

Frameworks

Spark, Apache Spark

Tools

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

Storage

MongoDB, PostgreSQL, Azkaban

2006 - 2012

Master's Degree in Mathematics and Computer Science

Aalto University - Espoo, Finland