Data scientist and software engineer with a background in computational engineering, simulations, machine learning, and engineering research. I live for taking zero to one. Specialties: Startup engineering, data science, machine learning, big data engineering, big data sensing systems, Internet of Things, simulation based prediction methods, machine condition monitoring and fault detection systems, software product design, sensor systems, computational engineering. Machine Learning and Data Science methods: supervised and unsupervised learning methods, recommender systems, NLP, deep learning, online learners, feature engineering, survival analysis, proportional hazard models, anomaly detection, search, reinforcement learning, markov-chain monte carlo, Bayesian methods, probabilistic graphical models, particle filter methods ML/DS Tools: mlpy/NumPy/PyBrain/scikit-learn/Shogun/Pandas (Python-based), Spark ML, MATLAB (and Octave), R, TIBCO Spotfire, various plotting and data visualization tools and libraries Big data processing/computing: Apache Spark, Hadoop MapReduce, MongoDB (Aggregations and GridFS) DB and distributed persistence: MongoDB, Hadoop, ElasticSearch, Amazon S3, Google DataStore, Postgres/MySQL, Cassandra, HBase, Hive, Redis, Aerospike, TitanDB, Tachyon, Avro MQ and data streaming: Kafka, Flume, Amazon Kinesis, ZeroMQ, ActiveMQ, Apache Storm, Spark Streaming

Founder and Chief Data Scientist @ Led team IOTA, one of the top three winning teams at the Stanford Startup Weekend 2013. From 2014 to Present (1 year) Manager of Data Science @ Data science and machine learning research, design, and development Leading rapid prototype development at Sysomos Labs. Managing the transition of Labs’ data science programs and applications to production. Product architecture and design, product management, processes design, mentoring, product communication. From 2015 to 2015 (less than a year) Toronto, Canada AreaPhD Graduate Researcher @ Topic: Design and Simulation of Industrial Information Systems and development of Anomaly Detection Systems. Thesis: Design, Simulation, and Evaluation of Industrial Information Systems, Case of Machine Condition Monitoring and Maintenance Management Systems Applied to Natural Resources Production Operations. Developed a framework for design and evaluation of industrial information systems. I developed and coded a novel simulation method called the probability model-linked discrete event simulation (PM-DES) for simulating stochastic industrial information systems in large scale industrial operations. Coded the stochastic discrete event simulator in Python using an object-oriented and process-based method. The simulator was designed and developed systematically with an extensive test suite (https://github.com/rezsa/minesim). Applied the PM-DES method combined with the analytic hierarchy process (AHP) to simulate and evaluate condition monitoring and maintenance management information systems for surface mobile mining operations. From 2009 to 2013 (4 years) Research Engineer @ Developed machine learning algorithms for reliability analysis and life prediction of artificial lift systems Developed statistical reliability and survival analysis of complex electro-mechanical systems Developed Computational Fluid Dynamics (CFD) models and simulation code for unconventional oil and gas production Developed reservoir simulation models of post thermal recovery heat extraction operations Managed engineering research projects as a project manager From 2008 to 2011 (3 years) Graduate Researcher @ Developed CFD models and code to research the effects of natural convection and horizontal winds on vapor diffusion in porous media, application to water transport on Mars. Developed CFD models to study the fluid flow and heat transfer around the Phoenix Mars Lander. This study was funded by the Canadian Space Agency (CSA) in collaboration with the Phoenix Mars Lander mission team that consisted of the National Aeronautics and Space Administration (NASA), CSA, and several universities led by the University of Arizona. Designed and performed experimental investigation of the effects of natural convection on vapor transport phenomena in porous media. From 2005 to 2008 (3 years)

Doctor of Philosophy (PhD), Industrial Information Systems and Machine Condition Monitoring, Engineering Management, 4.0 @ University of AlbertaStanford Ignite, Entrepreneurship/Entrepreneurial Studies @ Stanford University Graduate School of BusinessMaster of Science (MSc), Mechanical Engineering, Computational Fluid Dynamics, 4.0 @ University of AlbertaBachelor of Engineering (BEng), Mechanical Engineering, With Distinction @ University of Tehran Rezsa Farahani is skilled in: Simulations, Machine Learning, Data Science, Pattern Recognition, Entrepreneurship, Sensors, Data Mining, Internet of Things, Apache Spark, Numerical Analysis, Big Data, Meteor, scikit-learn, Deep Learning, Apache Kafka