🤵 Personal Information

email: Ihar.Nestsiarenia@gmail.com linkedin: https://www.linkedin.com/in/nesterione/ detailed version: CV (Full)

📊 Summary

With a 9-year background in machine learning, specializing in NLP and product development, I excel in leading projects from concept to production. Skilled in rapid prototyping, particularly integrating LLMs into system development, I thrive in agile, small product teams. Seeking Tech Lead roles to leverage my expertise in evolving machine learning technologies.

Key skills: NLP, LLMs, Information Search, LegalTech, Information Extraction, OCR, MLOps, AWS Sagemaker

🔨 Working Experience

Aug 2023 - Now: Machine Learning Engineer / Tech Lead (EPAM Systems)

Summary: Responsible for integrating and migrating MLOps from an acquired company, aligning with organizational standards. As part of the team, I’m also leading LLM prototypes for different business purposes.

Key Projects:

• Developed and led an LLM-based prototyping initiative for technical writers, significantly reducing workload and enhancing documentation quality
• Refined the LLM call strategy, leading to a 10x increase in processing throughput, enhancing system efficiency and performance.
• Designed a document annotation process and developed UI prototypes for new image and OCR annotation types, improving process efficiency after validating with the target team.

Technologies: Amazon Sagemaker, Glue, Textract, LLMs (GPT-4), Python.

Mar 2022 - Aug 2023: Machine Learning Engineer / Tech Lead (EPAM Systems)

Summary: Stepped in as Tech Lead mid-project for a U.S.-based insurance company’s information extraction team, focusing on optimizing backend processes and ML system design. Managed technical and process limitations to meet business deadlines.

Achievements:

• Overhauled development and release processes, reducing release time from 2 days to 1 hour.
• Improved system throughput by 11x, crucial for meeting project deadlines.
• Designed and implemented document search preparation and batch processing pipelines.
• Established data processing dashboards for better business transparency.
• Introduced MLOps practices, stabilizing ML delivery.

Technologies: Azure, Kubernetes, Keda, Elasticsearch, DEPS, Pytorch, ChatGPT, Github Copilot, Amazon Textract, PostgreSQL

2021 — Mar 2022: Lead Machine Learning Engineer / MLOps (EPAM Systems)

Summary: Responsible for utilizing AI to address challenges faced by legal professionals, including designing and implementing search algorithms, developing metrics, establishing pipelines, and automating tasks. Integrated SageMaker, streamlined development process with pipelines, and improved delivery with MLOps practices.

• Implemented MLOps practices to accelerate development and maintain data, code, models, and documentation.
• Improved ML development process with criteria, goals, metrics, and a metrics framework.
• Led a hackathon team to runner-up prizes and implemented ideas to enhance the product.

Technologies: Tensorflow, Keras, scikit-learn, spaCy, BM25, word2vec, Solr, DVC, Sagemaker, Python, Docker

2020 — 2021: Lead Machine Learning Engineer / AI Architect (EPAM Systems)

Summary: Played a crucial role in designing and implementing document processing services for a case-management system for lawyers. Conducted R&D, prototyping, and implemented machine learning models and metrics to ensure accuracy and performance.

• Streamlined R&D work in data science and transitioned from research to production.
• Enhanced performance of the pdf layout recognition pipeline and organized data versioning and experiment management.
• Implemented and automated data labeling, data quality, and reporting process.

Technologies: flair, spacy, huggingfaces, nlpaug, sklearn, flask, python, docker, pytorch, AWS Step Functions, AWS SQS, git, DVC, s3, scrum, kanban, jira, tesseract, ABBYY finereader, elasticsearch

2019 — 2020: Lead Machine Learning Engineer / Search Engineer (EPAM Systems)

Summary: Worked on ML algorithms, ETL pipelines, model deployment, and result analysis for a legal tech product targeting EU markets. Collaborated with business stakeholders to implement ranking algorithms, language models, and various NLP models.

• Developed POC for business validation and implemented core service architecture.
• Implemented NER algorithm, optimized for millions of documents.
• Improved model performance and designed API for analytics service.
• Created prototype for vector-based search at scale using Annoy library.

Technologies: flask, python, java, docker, AWS, TensorFlow projector, MLFlow, git, jira, solr, keras, stanfordnlp, gensim, sklearn, word2vec, BPE embeddings, fasttext, solr, elasticsearch

2018 — 2019: Senior Machine Learning Engineer at R&D Team (EPAM Systems)

Summary: Involved in AI-related projects and POCs, including deep learning, topic modeling, document classification, and knowledge management. Responsible for deploying and integrating models in production.

• Successfully delivered a POC for unsupervised topical extraction for Legal Jurisprudence using LDA and clustering algorithms.
• As the first member of the AI team, I helped to establish the AI delivery pipeline to production and was instrumental in hiring additional AI engineers.

Technologies: Tensorflow, Keras, scikit-learn, bigARTM, NLTK, spaCy, Fasttext, BM25, word2vec, gensim, Matplotlib, Jupyter Notebook, Node.js, Java, XSLT, and Elasticsearch

2016 — 2018: Senior Software Engineer / Data Engineer (EPAM Systems)

Summary: Assisted in the migration of a backend research platform for lawyers, focusing on improving accessibility and searchability. Responsible for batch processing of content and metadata, as well as delivering content to the search engine.

• Addressed peak load issues by integrating message brokers as middleware between services.
• Enhanced delivery quality through the integration of linters, static scanners, and configuring Sonar Cube.
• Recognized with a company award as a “Rising Star” for dedication and focus on process improvement.

Technologies: Elasticsearch, graph databases, Semantic Web, RDF/OWL, SPARQL Jena-TDB, JBoss Fuse, Tomcat, Apache Fuseki, ELK, Kibana, Sonar, FindBugs, PMD, Checkstyle, Winscp, Bamboo CI, Git, JIRA, Maven, Ant, Linux, Cron, Java 7, Java EE, ActiveMQ, Spring 3, REST, SOAP, Tomcat, JBoss Fuse, Jena, XSLT, RDF, XML, XPath, Semantic Web, JUnit, Cucumber, Camel, Blueprint, Log4J, Lombok.

🧑🏻‍🏫 2018 — 2019: Senior Teacher of Information Technologies Department — GSTU by P. Sukhoi

🧑🏻‍🏫 2015 — 2016: Senior Instructor (Java) — Educational Center “IT Class”

🧑🏻‍🏫 2014 — 2016: Assistant of Information Technologies Department - GSTU by P. Sukhoi

🎓 Education

• 👦🏻 2014 — 2016: Master of Science of Sukhoi state technical university of Gomel

  Department: Mathematical modeling, numerical methods and program complexes

• 👦🏻 2014 — 2016: Master of Science of Saint Petersburg National Research University of Information Technologies, Mechanics and Optics - ЛИМТУ (при НИУ ИТМО)

  Department: Computer Engineering and Design

• 👶🏻 2009 — 2014: Bachelor of Sukhoi State Technical University of Gomel

  Department: Information Technology

🧭 Other activities

• 🚀 Product Launching
  • Experienced in driving and leading pet-projects, assembling and managing teams, developing prototypes, and successfully acquiring users. Skilled in conducting user research, and implementing strategies to attract and engage users.
• 📢 Driving Communities
  • Then I joined the DataZen community and have taken on a leadership role in managing the community’s news stream using ML algorithms to prepare digests.
• 🦉 Advising and Mentoring
  • I am a seasoned trainer and advisor with experience in a variety of disciplines including Java, Python, and Machine Learning. I have also been actively involved in mentoring activities, providing guidance and direction to individuals and teams.

  last update: March 1, 2023

back