$$$$
{{ $t($store.state.user.experience_value_in_dollars) }}
Expert
{{ $t($store.state.user.experience_search_name) }}
0
jobs
Data scientist/Predictive modeller/Software developer/Telecom engineer
Krzysztof Fajst
,
Hatfield, United Kingdom
Experience
Other titles
Skills
I'm offering
Fifteen years of international experience in the telecoms industry in both R&D and customer areas. Very strong software design, testing and troubleshooting skills together with customer support and verification skills.
Seven years as Data Scientist Consultant in building of predictive models for financial data using different techniques like Artificial Intelligence/Machine Learning, Digital Signal Processing, Statistics and Econometrics and different programming languages (MATLAB, PYTHON, R, MQL, C/C++, SQL, CUDA, JAVA)
Data engineer/Software developer for Energy Systems Catapult in Birmingham
Data Scientist //Software developer /Predictive modeler in Affinity Water, Hatfield
Seven years as Data Scientist Consultant in building of predictive models for financial data using different techniques like Artificial Intelligence/Machine Learning, Digital Signal Processing, Statistics and Econometrics and different programming languages (MATLAB, PYTHON, R, MQL, C/C++, SQL, CUDA, JAVA)
Data engineer/Software developer for Energy Systems Catapult in Birmingham
Data Scientist //Software developer /Predictive modeler in Affinity Water, Hatfield
Markets
United Kingdom
Language
German
Good
English
Fluently
Polish
Fluently
Russian
Good
Ready for
Larger project
Ongoing relation / part-time
Full time contractor
Available
My experience
2018 - ?
job
Data Scientist - Software Developer
Affinity Water.
Predictive modeler
Research, system design and development of Python Anomaly Detection application which detects pressure/flow anomalies in water systems. Using Python 3.7 (NUMPY, SCIPY, PANDAS, SCIKIT-LEARN, MATPLOTLIB, PYTDS, PYOBC, PYWT, JOBLIB, MULTIPROCESSING, RAY, NUMBA, WEAVE, CYTHON). Various regression algorithms (SVR, Lasso, Ridge, Elastic Net) and different denoising techniques
(Median, Wavelet, Zero Lag) were used to achieve high accuracy results. Additional tools involved: MSSQL server, AWS, Docker. C/C++ design of various functions of the system to achieve high speed of processing. Building, integration and deploying both in MS Win10
and Linux Ubuntu AWS environments. Implemented system improved detection measures around 10x in case of recognition rate, 8 times in case of miss rate and 2 times in case of response time comparing to current commercial WaterNet system.
Research, system design and development of slow leak detection Python application. Various trend and jump detection methods were used (thresholding, moving averages crossover, polynomial regression). Modelling slow leaks using EPANET tool and ArcGIS Nighttime Flow Analysis tools.
Research, system design and development of Python Anomaly Detection application which detects pressure/flow anomalies in water systems. Using Python 3.7 (NUMPY, SCIPY, PANDAS, SCIKIT-LEARN, MATPLOTLIB, PYTDS, PYOBC, PYWT, JOBLIB, MULTIPROCESSING, RAY, NUMBA, WEAVE, CYTHON). Various regression algorithms (SVR, Lasso, Ridge, Elastic Net) and different denoising techniques
(Median, Wavelet, Zero Lag) were used to achieve high accuracy results. Additional tools involved: MSSQL server, AWS, Docker. C/C++ design of various functions of the system to achieve high speed of processing. Building, integration and deploying both in MS Win10
and Linux Ubuntu AWS environments. Implemented system improved detection measures around 10x in case of recognition rate, 8 times in case of miss rate and 2 times in case of response time comparing to current commercial WaterNet system.
Research, system design and development of slow leak detection Python application. Various trend and jump detection methods were used (thresholding, moving averages crossover, polynomial regression). Modelling slow leaks using EPANET tool and ArcGIS Nighttime Flow Analysis tools.
Net, Processing, Server, Software, System Design, Development, Mssql server, Developer, Ubuntu, Algorithms, Design, Integration, C, MSSQL, Research, Docker, AWS, Linux, Python
2017 - 2018
job
Data engineer - Software Developer
Energy Systems Catapult.
Predictive modeler
Python programming for EPO (Energy Path Operation) tool. Using Python 3.6
(NUMPY, SCIPY, PANDAS) and Python 2.7 for QGIS application (PyQGIS)
MATLAB - SQL 2016 Server integration and programming. Cluster analysis and statistical testing (ANOVA, T-test, SAS JMP Pro) for measuring
similarity between different clusters in different data sets. Developing data set generator to generate UK housing data set based on Census statistical data.
MATLAB/SIMULINK design and model optimization. Estimating SIMULINK house Model Parameters, Sensitivity Analysis, Monte Carlo simulations and Response Design Optimization.
Predictive analytics of energy load flow base on housing and occupancy data (scikit-learn, Google Cloud Machine Learning Engine, TensorFlow, Keras, pySpark, MATLAB Neural Net toolbox) Multi target regression of voltage drops based on IPSA simulation data. Fitting and simulating load distributions using Statistical and Machine Learning MATLAB toolbox.
Agile environment, SCRUM, JIRA, Confluence.
Python programming for EPO (Energy Path Operation) tool. Using Python 3.6
(NUMPY, SCIPY, PANDAS) and Python 2.7 for QGIS application (PyQGIS)
MATLAB - SQL 2016 Server integration and programming. Cluster analysis and statistical testing (ANOVA, T-test, SAS JMP Pro) for measuring
similarity between different clusters in different data sets. Developing data set generator to generate UK housing data set based on Census statistical data.
MATLAB/SIMULINK design and model optimization. Estimating SIMULINK house Model Parameters, Sensitivity Analysis, Monte Carlo simulations and Response Design Optimization.
Predictive analytics of energy load flow base on housing and occupancy data (scikit-learn, Google Cloud Machine Learning Engine, TensorFlow, Keras, pySpark, MATLAB Neural Net toolbox) Multi target regression of voltage drops based on IPSA simulation data. Fitting and simulating load distributions using Statistical and Machine Learning MATLAB toolbox.
Agile environment, SCRUM, JIRA, Confluence.
Tensorflow, Cluster Analysis, Energy, Energy, Google, Server, Software, Keras, Testing, Confluence, Developer, Predictive Analytics, Net, SAS, Design, Analytics, Integration, Test, Google cloud, Matlab, Cloud, Agile, Jira, Machine learning, Scrum, Python, Sql
2007 - 2017
job
Data Scientist
VEGA Consulting LTD.
Predictive modeler
• Software design using PYTHON, MATLAB, R, and C++. Researching, designing, implementing and back testing different 'whatif' and trade filtering scenarios for trading system e.g. 'time stop loss/exit', 'group stop loss/exit', 'partial position trade' and 'equity curve trade' with aim to improve trading system performance and decrease trading risk.
• Denoising of market data using different methods (Ehler SuperSmoother, Wavelet and Huang's Empirical Mode Decomposition). More info at http://www.trade2win.com/boards/trading-software/105880-3rd-generation-nn-deep-learning-deep-belief-nets-restricted-boltzmann-machines-20.html
R programming to design real time stationarity test procedure and apply it to trading system. Methods used DF, ADF, KPSS, Phillips-Peron, PSR, Wavelet.
Integration of real time stationarity test procedure with trading system, offline filtering transaction database based on unit root test result.
Creating high performance multicore server infrastructure to obtain high accuracy results in reasonable time based on MATLAB cluster and R (multicore and parallel packages, Big Data implementation)
• Software design using PYTHON, MATLAB, R, and C++. Researching, designing, implementing and back testing different 'whatif' and trade filtering scenarios for trading system e.g. 'time stop loss/exit', 'group stop loss/exit', 'partial position trade' and 'equity curve trade' with aim to improve trading system performance and decrease trading risk.
• Denoising of market data using different methods (Ehler SuperSmoother, Wavelet and Huang's Empirical Mode Decomposition). More info at http://www.trade2win.com/boards/trading-software/105880-3rd-generation-nn-deep-learning-deep-belief-nets-restricted-boltzmann-machines-20.html
R programming to design real time stationarity test procedure and apply it to trading system. Methods used DF, ADF, KPSS, Phillips-Peron, PSR, Wavelet.
Integration of real time stationarity test procedure with trading system, offline filtering transaction database based on unit root test result.
Creating high performance multicore server infrastructure to obtain high accuracy results in reasonable time based on MATLAB cluster and R (multicore and parallel packages, Big Data implementation)
Integration, Http, Server, Mode, Software, Software design, Testing, Infrastructure, Implementation, It, Design, Test, Matlab, R, C, Database, Big Data, HTML/CSS/Javascript, Python, Html
2012 - 2012
job
Integration Engineer
Ericsson.
Sweden. Working as a member of GIW test team for EvoET 8200.2 project (Evo Controller) which implements full IP transmission between BSC and RBS. System integration and troubleshooting of different problems related to new software releases (agile/SCRUM development) on all CP, RP and HW level (MSC-BSC/BSS). Verification of different problems related to new IP AUP protocol by analyzing of Wireshark traces. Writing Ericsson TRs related to found problems and cooperation with different design teams in troubleshooting of those problems.
Design, Scrum, Writing, Agile, System Integration, Test, Integration, Development, Software
My education
?
-
1993
Technical University Lodz
Unspecified, Electronics & Electrical Engineering
Unspecified, Electronics & Electrical Engineering
Krzysztof's reviews
Krzysztof has not received any reviews on Worksome.
Contact Krzysztof Fajst
Worksome removes the expensive intermediaries and gives you direct contact with relevant talent.
Create a login and get the opportunity to write to Krzysztof directly in Worksome.
38100+ qualified freelancers
are ready to help you
Tell us what you need help with
and get specific bids from skilled talent in Denmark