Personal details

Melih Ü. - Remote data scientist

Melih Ü.

Senior AI Engineer
Based in: 🇹🇷 Turkey
Timezone: Istanbul (UTC+3)

Summary

Highly skilled and accomplished Deep Learning expert with 7+ years of experience consist of both Computer Vision and NLP and 4+ years of technical management experience. Adept at creating and implementing advanced machine learning pipelines, designing efficient backend systems, and managing technical teams to ensure the successful delivery of complex projects. I have built ⭐1.5K GitHub repo, called DemoGPT which is about prompt-based LLM application development. With DemoGPT, I aimed to democratize the LLM-based application development.

Work Experience

Senior Python Developer
Turing | Nov 2021 - Dec 2023
Python
Data Science
Deep Learning
PyTorch
Large Language Models
  • Prepared code based dataset and train a GPT model to enhance the coding ability of the LLM side of the conversation model. Tried different finetuning strategies to decrease the number of parameters while preserving the accuracy.
  • Contributed to the development of the most popular LLM-based chatbot model having GPT architecture.
  • Designed and implemented efficient and scalable algorithms for pre-processing, training, and evaluation of large-scale deep learning models.
  • Developed and optimized software components to enable high-speed inference and seamless integration with various production systems. Conducted extensive experiments to evaluate and fine-tune the performance of the chatbot model on a range of natural language understanding tasks.
  • Developed novel techniques for transfer learning in deep learning models, specifically applied to the LLM-based chatbot model, resulting in improved performance and faster convergence.
  • Implemented advanced natural language processing algorithms to enhance the chatbot model's understanding and generation of code-related queries and responses.
  • Optimized memory utilization and runtime efficiency of the chatbot model, enabling it to handle large-scale conversations with minimal resource overhead.
  • Researched and implemented state-of-the-art techniques, such as attention mechanisms and transformer architectures, to enhance the chatbot model's contextawareness and ability to handle complex coding scenarios
Head of Artificial Intelligence
Mova AI | Feb 2023 - Aug 2023
Python
Flask
Leadership
PyTorch
AWS (Amazon Web Services)
OpenAI APIs
Large Language Models
  • Created the architecture and implemented complex system pipelines utilizing Large Language Models (LLMs)
  • Fintuned custom 10B+ LLM on bank specific dataset on multi-gpu system architecture.
  • Implemented self-refining technique designed for the bank assistant tool. Enabled custom LLM to execute API calls, effectively retrieving necessary widgets and displays for the desktop application, thus enhancing system speed and performance.
  • Integrated real-time processing and display capabilities in the desktop application, enhancing user experience through quicker response times.
  • Used specialized knowledge in AI to design custom LLM-based pipelines, improving the quality and performance of our systems.
  • Utilized innovative prompt engineering techniques to enhance the functionality and reliability of the AI systems.
  • Integrated speech-to-text models for real-time transcription retrieval, streamlining communication and improving the overall performance of the bank assistant.
  • Enabled LLMs to execute API calls, effectively retrieving necessary widgets and displays for the desktop application, thus enhancing system speed and performance.
  • Led the adoption of AI technologies in enhancing customer representative performance, leading to faster response times and improved customer satisfaction.
  • Encouraged cross-functional collaboration among engineering, data science, and customer service teams, ensuring effective implementation and use of AI tools and technologies.
  • Led the development of a robust backend architecture to serve the desktop application, ensuring its seamless operation across multiple platforms and services.
  • Provided regular updates to key stakeholders, including executive leadership and board members, on project progress, risks, and outcomes.

Education

Hacettepe University
Master's degree・Computer Science
Jan 2022 - Aug 2023
Bilkent University
Bachelor's degree・Computer Science
Aug 2015 - Jul 2020

Personal Projects

DemoGPTIconOpenNewWindows
2023
Python
Streamlit
OpenAI APIs
Langchain
Large Language Models
DemoGPT is a revolutionary open-source initiative that is reshaping the landscape of Large Language Model (LLM) based application development. At the heart of DemoGPT, the capabilities of GPT models come to life, driving the automatic generation of LangChain code. This process is enriched with a sophisticated architecture that translates user instructions into interactive Streamlit applications DemoGPT has good stats: - On GitHub, it has collected more than 1.5k stars. - On PyPi, demogpt library has more than 26k downloads - It has been cited by 3 research papers in arxiv.org - It has been shared by many youtube channels and newsletters.