🤵 Personal Information

Full name: Ihar Nestsiarenia Current role: Machine Learning Engineer / Head of Machine Learning EPAM LT/LV

LinkedIn: https://www.linkedin.com/in/nesterione/

📊 Summary

Experienced Machine Learning Engineer with over 10 years of leading ML projects from concept to production. Specializing in Natural Language Processing, Document processing, and Search technologies. Proficient in the full spectrum of NLP—from statistical models to deep learning and Large Language Models. Skilled at rapid prototyping and building scalable solutions from scratch to validate business ideas.

Roles have included Staff Engineer, Machine Learning Engineer, and AI Architect, with a current focus on technical implementation and system design. I excel in agile, compact teams, efficiently validating ideas and delivering production-ready solutions.

Open to consulting and mentoring opportunities, passionate about sharing knowledge and helping others grow in the AI field.

🤹 Core Skills

Domains: NLP, LLMs, Information Search, LegalTech, Information Extraction, OCR, Document Processing, Prototyping, Rapid Development, MLOps, LLMOps

Technologies: Python, Java, TensorFlow, PyTorch, Elasticsearch, Solr, LangChain, LangGraph, Argo, Langfuse, SageMaker, AWS, GCP, Azure, OpenAI API, GPT-4, Vector Databases (Qdrant, Chroma), MLOps Practices, CI/CD Pipelines, Git, DVC, Kubernetes, Docker

🔨 Professional Experience:

💻 2018 — now: EPAM Systems

July 2024 - Now: Lead AI Engineer at R&D Lab / AI Architect

• Leading development of GenAI applications tailored to internal business units
• Driving R&D for emerging GenAI solutions and establishing best practices
• Enhancing codebases with software engineering best practices for modularity
• Mentoring team members and conducting workshops to share knowledge

Achievements:

• Natural Language Query Prototype: Created a prototype translating natural language into Elasticsearch queries
• Vector Database Standards: Set guidelines for selecting vector databases based on project needs
• Retrieval Evaluation Template: Developed a standardized template, accelerating experimentation for teams
• Enhanced GenAI Codebase: Improved codebase with best practices for reusability and low coupling.
• Multi-Agent Systems Template: Designed a template adopted by other teams to speed up development
• Workshops and Training: Conducted sessions on building RAG systems and GenAI application evaluation.

Technologies: Kubernetes, vLLM, GCP, Qdrant, Chroma, LangGraph, LangChain, Argo, Langfuse

July 2024 - Now: Lead AI Engineer / AI Architect

• Transforming business challenges into AI solutions, building AI delivery processes from scratch.
• Designing tech stacks, organizing tech processes, developing AI strategies, and mentoring teams
• Designed multiple RAG systems for legal, code, and documentation assistance
• Developed agentic architectures for scalable AI systems

Achievements:

• Legal Assistant Development: Architected a legal assistant with a robust evaluation process.
• Code Assistant Development: Evolved a code assistant from a basic model to an agentic system.
• GenAI Application Management: Created a robust design integrating vector databases and workflow management.

Technologies: Elasticsearch, Chroma, Azure, Qdrant, LangGraph, LangChain, Argo, Langfuse

Aug 2023 - June 2024: Machine Learning Engineer / AI Engineer

Summary:

• Facilitated migration of ML ecosystems from an acquired companies.
• Identified bottlenecks, defined requirements, and led prototype development.
• Developed AI prototypes to improve internal processes using GenAI tools

Achievements:

• Content Scraping Agents: Designed a system using agentic architecture for faster parser implementation.
• Agent for technical writers: Created an LLM-based prototype for technical writers, reducing workload.
• LLM Pipeline Optimization: Achieved an 11x increase in processing throughput.
• Annotation Process Improvement: Designed a new annotation process with improved UI prototypes.

Technologies: AWS SageMaker, AWS Glue, AWS Textract, GPT-4, Python, OpenAI API

Mar 2022 — Aug 2023: Machine Learning Engineer / Tech Lead

• Tech Lead for an information extraction team at a US-based insurance company.
• Streamlined processes to meet critical deadlines.
• Optimized backend performance, refined development processes, and designed ML systems.

Achievements:

• Process Improvement: Reduced release time from 2 days to 1 hour.
• System Scaling: Increased system throughput by 10x.
• Document Indexing: Designed pipelines for document search preparation and batch processing, enhancing data enrichment and geo-coordinate extraction.
• Monitoring: Implemented data processing dashboards, increasing business transparency in extraction processes.
• MLOps Integration: Introduced minimal MLOps practices, including data pipelines and model registry, stabilizing ML delivery.
• Innovation and Training: Integrated GitHub Copilot and GPT, coaching the team.

Technologies: Azure, Kubernetes, Keda, Elasticsearch, DEPS, PyTorch, ChatGPT, GitHub Copilot, AWS Textract, PostgreSQL

2021 — 2023: Machine Learning Engineer

• Part of the EU product team, solving challenges for legal research problem using AI.
• Designed and implemented search algorithms and models to enhance legal research.
• Developed metrics, conducted experiments, established pipelines, and automated tasks

Achievements:

• SageMaker Integration: Streamlined development with pipelines and MLOps practices.
• ML Development Improvement: Established metrics and a framework for product tracking.
• Active Learning: Introduced data quality control measures.
• Evaluation pipelines: Designed and implemented evaluation pipelines for system performance.
• Hackathon Success: Led team to runner-up prizes and implemented ideas.

Technologies: TensorFlow, Keras, scikit-learn, spaCy, BM25, Word2Vec, Solr, DVC, SageMaker, Python, Docker

2020 — 2021: Machine Learning Engineer / AI Architect

• Development Team Lead for an AI team building document processing services, including systems design, model development, and productivization, creating ML infrastructure.
• Implemented an enrichment pipeline with models for classification, entity extraction, and layout recognition

Achievements:

• R&D to Production: Streamlined transition of research work to production. Delivered solution replaced 3rd party services.
• PDF Layout Recognition: Enhanced pipeline performance.
• Data Management: Organized data versioning and experiment reproducibility.
• Data Labeling: Implemented and automated data labeling, data quality, and reporting process using Apache Airflow and Labelstud.io.

Technologies:

• flair, spacy, huggingfaces, nlpaug, sklearn, flask, python, docker, docker-compose, jupyter lab, pytorch, AWS Step Functions, AWS SQS, git, DVC, s3, scrum, kanban, jira, tesseract, ABBYY finereader, elasticsearch.

2019 — 2020: Machine Learning Engineer

• Worked on ML algorithms, ETL pipelines, model deployment, and analysis for a legal tech product.
• Implemented ranking algorithms and classifications models for multiple languages.

Achievements:

• Developed POC for business validation using Solr and classification models, designed and implemented core service architecture
• Implemented NER algorithm using taxonomy and synonyms, optimized for millions of documents and 40k terms
• Improved model performance by 100x without quality degradation through reimplementation and parameter selection
• Designed API for analytics service, prepared documentation
• Created prototype for vector-based search at scale using Annoy library, integrated with Solr pipeline

Technologies:

• flask, python, java, docker, docker-compose, AWS, TensorFlow projector, MLFlow, git, jira, jupyter lab, solr, keras, stanfordnlp, gensim, sklearn, word2vec, BPE embeddings, fasttext, solr, elasticsearch.

2018 — 2019: Machine Learning Engineer at R&D Team

• Involved in AI projects like deep learning, topic modeling, document categorization, and voice bots.
• Deployed and integrated models in production, rapidly prototyping solutions.

Achievements:

• Successfully delivered a POC for unsupervised topical extraction for Legal Jurisprudence using LDA and clustering algorithms.
• Designed, developed, and fine-tuned a platform for automatic topic allocation to legal jurisprudence based on a hierarchical taxonomy, and successfully deployed it in production.
• Enhanced the quality of the voice bot by implementing vector search algorithms and intent detection.
• 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.
• Improved ML models by training custom language models (word2vec, GloVe)

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

• Assisted in migrating a backend research platform for lawyers.
• Performed batch processing of content and improved search accessibility.

Achievements:

• 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.
• Designed and executed a user migration tool to a new system, successfully migrating over 20,000 active users.
• Diagnosed and resolved memory leak issues using tools such as MAT and jstat.
• Enhanced system performance by fine-tuning GC parameters, resulting in an increase in throughput.
• Accelerated services configuration and deployment through integration of Docker and docker-compose for deployment.
• Received a company award as a “Rising Star” for my 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

I was a primary instructor and contributor to the course “Fundamentals of Intelligent Data Analysis,” where I conducted lectures and exercises. The course covered various aspects of data mining, with a focus on natural language processing. It included fundamental theoretical knowledge about machine learning and practical-oriented exercises using modern NLP and ML tools.

Central topics discussed during the course were: fundamentals of machine learning; model performance evaluation, metrics, cross-validation; NLP basics, data cleaning, preprocessing, lemmatization, and stemming; developing the pipeline for text classification problem; neural networks for textual analysis.

💼 2017 — 2020: Co-Founder Copeck — Loyalty system for SME

Summary: As a co-founder, I played multiple roles including Product Manager, backend developer, architect, and DevOps, in the development of a product for small and near-to-middle retail businesses.

The product provided client base management with a loyalty system, accounting of purchases, and worker’s KPI monitoring. The project underwent several pivots, and ultimately resulted in the implementation of a CRM with personal analytics for small businesses.

Our solution is easy to integrate, allowing business owners to start using it within minutes and start tracking their sales, collecting client base and managing loyalty program for them. It offers detailed information about the client base and transaction history, simplifies communication with clients, and provides advanced analytics on demand. The product has a Monthly Active User (MAU) of 3,000.

Team size: 6

Technologies:

Flask, Reactjs, Kotlin, Swift, JUnit, Python, Vue.js, Linux, Docker, pytest, gitlab ci, Docker/docker-compose, git, maven, Gitlab CI, bash, trello, miro, notion, MongoDb, java 8, Spring Boot, Loki, grafana

💼 2015 — 2016: Co-Founder of Pharco — B2B Pharmacy Consultant

Summary: The product was designed to solve several problems, including the recommendation of related products, which increased sales and enhanced client loyalty, and semantic search, which enabled search by symptoms and provided useful guides, as well as smart filtering for specific clients, such as pregnant women, lactating women, or children. The product also offered recommendations alternatives based on the official anthology of medicines. The project was partially acquired.

Team size: 8

Responsibilities: As a co-founder, my responsibilities included serving as a Product Manager, Technical Leader, where I organized the SDLC process, controlled code quality, configured CI/CD, and automated processes, Backend developer where I implemented the search system including fuzzy matching, ranking, and search by anthology graph, and developed a recommendation system based on rules, and finally, I was responsible for OPS, server configuration, proxies, and deployment management.

Technologies: Java 8, Spring MVC, Spring Security, Spring Data, Spring Boot, JSP, For admin-panel was used AngularJS. JPA/Hibernate, QueryDSL, Linux, Docker, JUnit / Spring Test Framework, docker-compose, git, Gradle, maven, Gitlab CI, Jenkins CI, bash, Python for data processing and aggregating from different sources, trello/gitlab issue tracker, Fiddler, MySQL (Used JPA/Hibernate, Spring Data)

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

As a course developer and trainer, I was responsible for creating and delivering a comprehensive Java programming course from scratch. The curriculum consisted of two sections: Basic Java and Java Enterprise Edition (Java EE). I achieved high student retention and more than half of the students successfully obtained employment in the IT industry.

💼 2015 — 2016: Co-Founder Arenda-online

As a co-founder, I was responsible for technical product management, DevOPS and backend development of an aggregation service for collecting advertisements for long-term rent. The service collected advertisements, deduplicated, and normalized them, and provided a search function with ranking, filtering, and sorting results. The project was closed as we were not able to find a suitable match between the product and the market.

The project included various components such as crawlers that ran on a schedule, a deduplication system that used fuzzy rules to detect the same advertisements from various sources, a RESTful API, a web application developed in React.js, and a server-rendering component based on PhantomJS that allowed us to create pre-rendered versions of the pages to help search crawlers index all pages of our app.

Team size: 2

Technologies: Java, Spring boot, React.js, PaaS OpenShift, maven, git, jsoup, mongodb, ODM morphia, docker, docker-compose, Linux, PhantomJS, Web Crawling, Search Engine Ranking, REST APIs, Product Management, DevOps

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

During my tenure, I contributed to core courses offered by the department. My responsibilities included:

• Improving the existing courses and developing practical exercises.
• Acting as a lecturer and participating in the examination process.
• Assisting with the organization of programming competitions.
• Fundamentals of parallel and multi-process data processing and network applications.
• Numerical methods for solving differential equations, including the Finite Difference Method and the finite element method.

🧭 Other activities

📢 Driving Communities

• I have a strong background in machine learning and have had the opportunity to develop the first ML training program in my hometown of Gomel (with my friend Pavel Goncharov).
• I also took initiative to create a local community of 100 people dedicated to the study and development of machine learning.
• 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.

🎓 Education

👨🏻 2016 — 2020: PhD (uncompleted) of Sukhoi state technical university of Gomel

Department: 05.13.05 Elements and devices of computer technology and control systems

Research domain: computer vision, object detection, vehicles tracking, traffic-light management, optimization

Summary: During my research, I focused on the integration of intelligent analytics and monitoring systems for road traffic.

My research centered on extracting information from video streams and developing optimization models to reduce traffic load. In a city where all roads and traffic lights are aware of road conditions in real time, the system could dynamically change traffic light regimes to normalize traffic flow.

I worked on optimization models that could be deployed on single-board computers. I developed a prototype for car tracking using OpenCV and deep neural networks, and presented my results at several international conferences, and published several papers on the topic.

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

Department: Mathematical modeling, numerical methods and program complexes

Diploma score: 10 (from 10)

Summary: As a continuation of my undergraduate studies, I conducted research on the modeling of dynamic transient processes using the Finite Element Method. My research resulted in the development of a modeling application that consisted of the following key components:

• A solver that employed the Finite Element Method to determine the distribution of heat generated by dynamic loads.
• A 3D web-based editor that enabled the composition of objects to be modeled and a visualization tool for displaying the results of the modeling process.

👦🏻 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

Diploma score: 5 (from 5)

Summary: I acquired knowledge of various approaches for designing web applications and gained proficiency in working with vector and raster graphics, including the basics of design. My final project involved the implementation of a 3D web editor using WebGL (Three.js) and Angular.js.

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

Department: Information Technology

Diploma score: 10 **(from 10)

Summary: During my student years, I gained research experience and participated in multiple conferences. I also presented a thesis related to my final project, which focused on the math modeling of transients processes. This project consisted of two parts: the application of the finite element method to the problem of heating a metal plate under a load, and the development of a software application with a visual editor, experiment management system, and custom math solver for solving problems.

back