Panayot P Senior ML Engineer with Data Engineering

AI and Machine Learning (6.0 yr.), Data Engineer

Summary

- Senior Machine Learning Engineer with extensive experience in providing innovative machine learning solutions and automation.
- Experience with ontology enrichment & transformation, Named Entity Recognition, recommendation systems, sentiment analysis
- Experience with Data Engineering stack
- Advanced skills in Python, Flask, FastAPI, Redis, Postgres, TensorFlow, PyTorch, Elasticsearch, Docker, and Hugging Face.
- Proven track record in data analysis projects implementation.

Work Experience

Senior Machine Learning Engineer

05/2024 – Present

Responsibilities: My colleagues and I are actively participating in a project focused on improving ontology as a service. In my role, I was tasked with devising and implementing processes to maintain and enrich the ontology, a critical component of a Named Entity Recognition (NER) application. Additionally, I participated in the company hackathon, collaborating with a team to develop a crop recommendation system. Currently, I’m leading the data analysis internship program.

Technologies: Python, FastAPI, Redis, PostgreSQL, Elasticsearch, Docker, PyTorch, Hugging Face

Senior Machine Learning Engineer

04/2023 – 05/2024

Responsibilities: As a member of the Quants department, my team and I were tasked with the responsibility of conceiving, reinforcing, and enhancing AI functionalities of our products. Some of the tasks were:

• personalized recommendations of news and research

• sentiment analysis on financial news

• development and improvement of models for selecting top news retraining to specific companies

• capturing the essence of a news article and transforming it into a video clip

• Created PoC that applies LLM to news summarization and improvement of search capabilities Additionally, I helped with the development of a user interface using ReactJS to exhibit these model capabilities to our clients.

Technologies: Python, Django, Redis, PostgreSQL, Tensorflow, Flask, Swagger, ReactJS, Docker, Elasticsearch, Hugging Face

Senior Machine Learning Engineer

11/2020 – 04/2022

Responsibilities: Engaged in a project aimed at collecting data from public companies to be distributed to credit-scoring institutions. My responsibilities included:

• Containerization of the project code base.

• Crawl companies’ websites without being banned.

• Create ongoing reports for the client.

• Improve the success rate of the company information found.

Technologies: Python, Django, Redis, PostgreSQL, Celery, Elasticsearch, Ansible, Docker

Machine Learning Engineer

05/2019 – 09/2020

Responsibilities: I was part of the R&D team, and the main objective was to create tools that could help the Support Team. Part of my tasks included optimizing the search results on the website, creating a chatbot, and improving the machine translation.

• Automating internal processes such as deployment of Machine Learning models on production.

• Finding and preparing bilingual corpora for training Google AutoML models.

• Data preparation and training of ML models.

• Actively following the latest trends in the field of Natural Language Processing.

Technologies: Python, Bash, Flask, Redis, PostgreSQL, Apache Solr, TensorFlow

Data Engineer

10/2018 – 05/2019

Responsibilities: I was part of the R&D team in the Experian Analytic Center of Expertise department. I’ve worked on external products and automation of internal processes. Other responsibilities included:

• Mentoring interns and junior data engineers.

• Created demos that were later used by the sales team to pitch new clients.

• Worked on the latest Experian product - Trusso, for which my responsibilities were: preparing training data, training classification models, validating that each trained model works correctly, and deploying it to production.

Technologies: Python, Bash, Apache Spark, Redis, PostgreSQL

Associate Data Engineer

03/2017 – 09/2018

Responsibilities: Mentoring interns and writing code reviews.

• Automation of internal processes.

• Worked on an internal product based on Apache Spark with the main purpose of helping the Data Scientists to process big chunks of data. Part of the job was: developing and testing new features, and writing documentation.

Technologies: Python, Bash, Apache Spark

Education

  • Master Degree in Data Mining 10/2018 – 02/2020
  • Bachelor Degree in Informatics 10/2012 – 01/2017