About
I am an active and committed individual who enjoys being part of teams and projects that involve challenges and new learning opportunities. My engineering background equips me with critical thinking skills and the ability to adapt to various circumstances, as well as a strong sense of self-directed learning.
Machine Learning Engineer & Acoustic Engineering Student
- City: Buenos Aires, Argentina
- Degree: Engineering
- Email: francobach47@gmail.com
👤 I'm Argentinian, an advanced student of Acoustic Engineering, currently working as a Machine Learning Engineer specializing in text-to-speech systems (TTS).
🎯 My primary interests lie in software development related to audio, specially in audio plugin development, digital signal processing (DSP), Machine and Deep Learning, among others.
🌱 I enjoy being part of environments that encourage both my technical and personal growth, while also contributing to the collective progress and development of a team.
🧠Currently, I work as a Machine Learning Engineer, specializing in the research and development of text-to-speech (TTS) technologies. This includes voice synthesis, cloning, conversion, and more, based on artificial intelligence.
📚 Furthermore, I am in the final years of the program, actively searching for a thesis topic focused on digital signal processing and machine learning to complete my studies.
Services
My academic and professional experience, being part of interdisciplinary teams and diverse projects, has helped me develop a range of skills and services that I am now able to offer. Among these, I highlight the following:
Acoustic Engineering
Extensive knowledge in various branches of audio and acoustics, with a special focus on digital signal processing. My field experience and engineering background have provided me with critical thinking skills and the ability to work effectively in interdisciplinary teams, whether in research, development, design, or other areas.
Artificial Intelligence
With a deep interest and expertise in Audio AI, Computer Vision, NLP, and other related fields, I have built a solid understanding of these areas. My skills are supported by a strong foundation in mathematics and statistics, developed through my engineering background. I also have practical experience with MLOps technologies and practices.
Software Development
Proficient in various programming languages with the ability to collaborate effectively within interdisciplinary teams in software development. I have advanced skills in Python and junior-level expertise in C++ (among others), with a particular interest in developing audio plugins and audio-related software.
Resume
Education
Acoustic Engineering
2018 - Present
National University of Tres de Febrero, Buenos Aires, Argentina
Bachelor’s + Master’s degree program focused on the study of acoustics, electroacoustics, digital signal processing (DSP), vibration and noise analysis, audio electronics, among others, with a strong foundation in maths and physics.
Currently, I am in the final years of the program, actively searching for a thesis topic focused on digital signal processing and machine learning to complete my studies.
Certificates
MLOps Zoomcamp
DataTalksClub
LLM Zoomcamp
DataTalksClub
NLP Course
Hugging Face
Computer Vision Course
Hugging Face
Docker for the absolute beginner
KodeKloud
Feature Engineering
Kaggle
Programming in Python
UNSAM
Frontend Web Developer
UNTREF
Professional Experience
Jr Machine Learning Engineer
July 2023 – Present
MecanTronic
- R&D in multilingual text-to-speech (TTS) technologies, using systems such as: GE2E, Tacotron 2, FastPitch, TorToiSe, HiFiGAN, WaveRNN.
- Development and study of speech-to-text and text-to-text systems.
- Containerization of Machine Learning applications using Docker.
- Implementation of AWS CloudWatch for metrics monitoring in Machine Learning systems in production.
- Design of a proof of concept in robotic & AI project, using Raspberry Pi and ROS 2.
- API Gateway development using FastAPI and MySQL.
Jr Machine Learning Engineer (Apprenticeship)
April 2023 – June 2023
Infiniem Labs
- Research, study, and implementation of text-to-speech (TTS) systems for voice cloning in Rioplatense Spanish.
- Training AI models on GPU cloud instances (AWS EC2).
- Management of virtual environments with Poetry and tracking of ML model training with MLflow.
- Exploratory Data Analysis (EDA) of datasets for analysis and training of TTS systems.
- Development of dataset and functionalities for training and analysis of Computer Vision model.
- Acquiring good practices in software development through team work with Scrum methodology.
Projects
Mi Identidad Vocal
Development of voice synthesis and cloning software for former national deputy Jorge Rivas. By using audio recordings from his sessions in the Chamber of Deputies, his voice was reconstructed through text-to-speech (TTS) models, thus restoring his vocal identity.
Portfolio
These are some of the projects I have been a part of during my academic and professional career. They involve analysis, research, study, and development in various branches associated with audio and acoustics.
More projects coming soon.
- All
- Acoustics
- Artificial Intelligence
- Audio Plugins
- Digital Signal Processing
