Ana is currently unavailable
Ana Mamatelashvili, PhD
Verified Expert in Engineering
Data Science Developer
Tbilisi, Georgia
Toptal member since January 24, 2022
Bio
Ana is a problem solver that enjoys finding and fixing needs while supporting her team. As a data scientist with a Ph.D. in pure maths and a current obsession with MLOps, she experiences profound joy in projects such as commit passing CI/CD, BI investigation to understand the process to model, project demos, data versioning, and graphs. So far, Ana successfully trained and logged models, saw an abstract pure maths concept improving her model, and had her code dissected at a code review.
Portfolio
Quantori
Python, Transformers, AlphaFold, Amazon Web Services (AWS)...
Caterpillar
Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT)...
Supernova
Python, Rasa Open Source, PyCharm, Graphs, Machine Learning, Chatbots...
Experience
- Graphs - 10 years
- Python - 6 years
- R - 4 years
- Natural Language Processing (NLP) - 3 years
- Amazon Web Services (AWS) - 3 years
- Generative Pre-trained Transformers (GPT) - 3 years
- Rasa Open Source - 2 years
- Information Extraction - 2 years
Preferred Environment
PyCharm, Amazon SageMaker
The most amazing...
...project I've developed is a document processing and information extraction application that reduced processing time for insurance claims by 30%.
Work Experience
Principal Machine Learning Engineer
2022 - 2022
Quantori
- Studied AlphaFold, its technical details, usage options, deployment options, analytics, and evaluation methods to aid potential company clients in incorporating AlphaFold in their processes.
- Coached colleagues and helped manage project delivery.
- Consulted on the best R environment set up for data scientists.
Technologies: Python, Transformers, AlphaFold, Amazon Web Services (AWS), Google Cloud Platform (GCP), High-performance Computing (HPC), Image Segmentation, R, RStudio, Data Science
Data Scientist (Full-time Contractor)
2021 - 2022
Caterpillar
- Joined the team in the middle of a fast-paced project five weeks before the end of the year and helped shape the project direction and deliverables to achieve them.
- Introduced novel NLP approaches to the team that improved problem-solving approaches.
- Hosted a talk on one of the packages to the company's wider team.
Technologies: Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), PyCharm, Amazon SageMaker, Python, Graphs, Machine Learning, SQL, SpaCy, Amazon Web Services (AWS), Data Science, Spark
Lead Data Scientist (Part-time Contractor)
2021 - 2021
Supernova
- Directed data analysis to diagnose problems in the Georgian language chatbot prototype that the team was working on. As a result, we discovered problems and direct our efforts to the highest impact issue.
- Made a recommendation to switch to the Rasa open-source chatbot framework and facilitated the switch, which resulted in a drastic increase in chatbot performance.
- Recommended adjusting the chatbot data structure to be more ontology-based and facilitated the adjustment process, making it possible to effectively maintain and validate the data mode.
Technologies: Python, Rasa Open Source, PyCharm, Graphs, Machine Learning, Chatbots, Data Science, Minimum Viable Product (MVP)
Senior Data Scientist | Data Scientist | Associate Data Scientist
2019 - 2021
Eliiza
- Developed an information extraction and document processing application that saved our client 30% of processing time. As a result, we received more work from this client, and our team developed a product offering based on this prototype.
- Managed and mentored two interns that joined my information extraction project for a few weeks.
- Conducted technical interviews and hired five of my team members, including our manager.
- Worked on a variety of client projects, delivering high-quality data science work while supporting the internal team with presales, recruitment, and mentorship work.
Technologies: Python, R, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Information Extraction, Google Cloud Platform (GCP), Sales Presentations, Mentorship, Recruitment, PyCharm, Amazon SageMaker, Graphs, Machine Learning, Rasa Open Source, Chatbots, SQL, SpaCy, Knowledge Graphs, Tidyverse, Geospatial Analytics, Dialogflow, Databricks, Amazon Web Services (AWS), Data Science, Spatial Analysis, Spark, Minimum Viable Product (MVP)
WebWork Research Assistant | Sessional Tutor
2017 - 2019
The University of Melbourne
- Developed algorithms to create "Calculus 2" online assignment content on WebWork using Perl and PG programming languages and maintained the content afterward.
- Led tutorials for various mathematics courses in the School of Mathematics and Statistics.
- Let tutorials for "Logic: Language and Information" at the School of Historical and Philosophical Studies.
Technologies: Perl, Mathematics
Postdoctoral Fellow
2014 - 2016
Auburn University
- Developed course content such as lectures and assessment methods, delivered lectures, and analyzed students' performance. I lectured for six courses, including several large classes in analysis, probability, and statistics.
- Built novel research methodologies, recursive algorithms, and constructions, applying them to solving problems in analysis and topology.
- Studied the feasibility of past research methodologies and reformulated long-standing mathematical problems into ones that could be tackled with models and techniques, from graph theory to logic, model theory, set theory, analysis, and topology.
- Published one research paper and submitted two more.
- Hosted three invited talks—one of them a semi-plenary talk at a major annual conference in my research field—as well as four contributed conference talks. I also gave ten seminar talks in my home department.
Technologies: Lecturing, Graphs, Mathematics
Teaching Assistant
2009 - 2014
University of Pittsburgh
- Lectured and conducted recitations for mathematics courses.
- Conducted lab sessions for mathematics courses as part of my role.
- Organized student seminars within my research group and the department of mathematics and statistics.
Technologies: Mathematics, Lecturing, Graphs
Financial Risks Manager
2008 - 2009
Aldagi BCI
- Worked closely with reinsurers to perform data analysis and reporting to best address their goals. As a result, we closed the first reinsurance treaty for financial risks for the company.
- Collected, maintained, processed, and analyzed financial risks data. I also collaborated with the sales and legal teams of AldagiBCI to clarify business processes, identify reliable data sources, and collect high-quality data.
- Developed and implemented mathematical and statistical methods to model data and draw insights. I used numerical analysis methods to develop novel algorithms to compute the key indicators regarding risk exposure and management.
Technologies: Excel 365, Data Analysis, Statistics
Experience
Information Extraction
Our team designed, implemented, and deployed to production an information extraction and post-processing solution to automate insurance claims processing.
Our application receives an image, sends it through an OCR component, processes the raw OCR output according to the insurance company's business logic, and prepopulates the claim form with all the fields—like price, service item, provider, and more.
The team consisted of a machine learning engineer—for deployment and integration—and myself as a data scientist— performing BI research, problem scoping, and solution design and implementation.
The solution achieved a 30% reduction in average handling time for human review of the claims.
Our application receives an image, sends it through an OCR component, processes the raw OCR output according to the insurance company's business logic, and prepopulates the claim form with all the fields—like price, service item, provider, and more.
The team consisted of a machine learning engineer—for deployment and integration—and myself as a data scientist— performing BI research, problem scoping, and solution design and implementation.
The solution achieved a 30% reduction in average handling time for human review of the claims.
Chatbot Scoping
I conducted a technology review, project scoping, and use case development for a chatbot for one of the big four Australian banks.
I worked across several teams to achieve this, including security, cloud engineering, and customer service teams.
I worked across several teams to achieve this, including security, cloud engineering, and customer service teams.
Coaching
I coached a data scientist to build a general solution for utilizing rich insurance member and claims data to support digital sales and healthier lifestyle campaigns.
The project was deployed on DataBricks with R.
The project was deployed on DataBricks with R.
Chatbot Evaluation Framework
I designed and implemented a deployment-ready custom model iteration and evaluation process for a chatbot for a major insurance company. The new process was integrated a couple of months later.
I worked closely with the chatbot maintenance team to identify the best suitable solution.
I worked closely with the chatbot maintenance team to identify the best suitable solution.
Labour Market Study | Independent Work
This project focused on studying the online presence of the Georgian labor market. The project's scope extended to identifying the largest and the most reliable data sources, developing methodologies and implementing algorithms to collect, consolidate, and maintain the data, designing mathematical and statistical methods to analyze the data, and publishing results and conclusions on the project's website.
Connectedness Properties in Graphs
https://arxiv.org/pdf/1209.5451.pdfIn this project, I focused on studying strong arcwise connectedness properties in nite graphs and related spaces. Among other work, I established a threshold connectedness degree of seven points and developed methods and algorithms to characterize graphs of lower connectedness degrees.
Publications (besides the one available in the link above):
• https://arxiv.org/pdf/1209.5454.pdf
• https://arxiv.org/abs/1801.00179
Publications (besides the one available in the link above):
• https://arxiv.org/pdf/1209.5454.pdf
• https://arxiv.org/abs/1801.00179
Complexity of Ordered Structures
https://www.cambridge.org/core/journals/journal-of-symbolic-logic/article/abs/div-classtitlethe-tukey-order-on-compact-subsets-of-separable-metric-spacesdiv/345AAFFA060E02B4D0450748251C4F53This project was dedicated to studying order structures arising from real numbers and related spaces. Among other work, I developed an algorithm to recursively construct the maximal possible sized collection of ordered structures from the real numbers with differing order complexities, consequently answering a 40-year-old question in foundations of mathematics.
Publications (besides the one available in the link above):
• https://link.springer.com/article/10.1007/s11083-017-9423-6?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst
• https://arxiv.org/pdf/1606.06493.pdf
Publications (besides the one available in the link above):
• https://link.springer.com/article/10.1007/s11083-017-9423-6?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst
• https://arxiv.org/pdf/1606.06493.pdf
Education
2009 - 2014
Ph.D. in Mathematics and Computer Science
University of Pittsburgh - Pittsburgh, PA, USA
2004 - 2008
Bachelor's Degree in Mathematics and Computer Science
American University in Bulgaria - Blagoevgrad, Bulgaria
Certifications
FEBRUARY 2019 - PRESENT
Data Scientist Nanodegree Program
Udacity
Skills
Libraries/APIs
SpaCy, Tidyverse
Tools
PyCharm, Amazon SageMaker, Dialogflow
Languages
Python, R, SQL, Perl
Platforms
Amazon Web Services (AWS), RStudio, Google Cloud Platform (GCP), Databricks
Frameworks
Spark
Paradigms
High-performance Computing (HPC)
Storage
Graph Databases
Other
Natural Language Processing (NLP), Information Extraction, Graphs, Machine Learning, Chatbots, Rasa Open Source, Mentorship, Data Science, Datasets, Generative Pre-trained Transformers (GPT), Artificial Intelligence (AI), Minimum Viable Product (MVP), Geospatial Analytics, Recruitment, AlphaFold, Spatial Analysis, Knowledge Graphs, Sales Presentations, Statistics, Finance, Mathematics, Lecturing, Excel 365, Data Analysis, Transformers, Image Segmentation
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