Carlos Henrique Tarjano Santos, PhD

Profile Photo

Head of Data at Match<IT>, where I research, develop and implement NLP solutions with cutting-edge technology such as LLMs, LangChain, and Microsoft guidance. PhD in Production Engineering (UFF) using machine learning and DSP for real-time sound synthesis. Founder of Omnes Sonos Audio Plugins.

Education

EDUCATION

PhD in Industrial Engineering and Management (Revalidation 320240067419)   U.PORTO [Porto University] (07/03/2024 - 07/03/2024)

PhD in Production Engineering   UFF [Fluminense Federal University] (01/08/2018 - 28/07/2022)

Visiting Research Fellow at ICCMR   University of Plymouth (01/01/2020 - 31/03/2020)

MSc in Production Engineering   UFF [Fluminense Federal University] (01/03/2017 - 31/07/2018)

Bachelor's Degree in Production Engineering   CEFET [Federal Center of Technological Education] (01/03/2010 - 01/12/2015)

work

WORK

Match<IT> Head of Data (17/03/2023) Managing a small team developing and implementing humanlike conversational interfaces and textual similarity algorithms employing state-of-the-art machine learning, NLP, and Agile software development techniques.

Match<IT> IA/NLP Researcher (24/10/2022 - 17/03/2023) Designing and implementing improvements in the algorithm used to match tech sellers with tech buyers based on tabular and textual descriptions.

UFRJ [Federal University of Rio de Janeiro] Administrative Assistant (27/01/2009 - 15/12/2022) In Brazil, federal positions such as this are very sought after, as they offer tenure and paid study leave, among other perks. They require passing a selective process with thousands of candidates for each vacancy. Working for more than a decade in one of the largest universities in Latin America has allowed me to explore a wealth of work experiences and develop a solid network, while pursuing formal education. Among the functions I was able to perform are:
Assisting in the administration of the International Relations undergraduate program, including creating its visual identity, analyzing its scholarly production metrics, and evaluating student performance.
Managing all aspects of the Philosophy graduate program, from maintaining its website to analyzing its scholarly production metrics, besides developing multiple solutions to optimize and automate the work processes.
Serving as vice-chief of IFCS financial center, where I assisted in planning and executing various projects, besides overseeing the use of the annual budget.
Supervising the logistics of document flow in IFCS, while implementing and enforcing digitalization and automation solutions.

Publications

PUBLICATIONS

Carlos Tarjano : A general algorithm for the real-time emulation of pitched musical instruments and the singing voice. PhD Thesis - Production Engineering - Fluminense Federal University, 2022. dx.doi.org/10.22409/TPP.2022.d.11839251743.

Carlos Tarjano | Valdecy Pereira : An Efficient Algorithm For Segmenting Quasi-Periodic Digital Signals Into Pseudo Cycles: Application in Lossy Audio Compression. IEEE/ACM Transactions on Audio Speech and Language Processing, Volume 30, May 2022. doi.org/10.1109/TASLP.2022.3171969.

Carlos Tarjano | Valdecy Pereira : Envelope estimation using geometric properties of a discrete real signal. Digital Signal Processing, Volume 120, January 2022. doi.org/10.1016/j.dsp.2021.103229. Early manuscript available at arxiv.org/abs/2009.02860.

Carlos Tarjano | Valdecy Pereira : Neuro-Spectral Audio Synthesis: Exploiting characteristics of the Discrete Fourier Transform in the real-time simulation of musical instruments using parallel Neural Networks. Lecture Notes in Computer Science Volume 11730, September 2019. doi.org/10.1007/978-3-030-30490-4_30.

Carlos Tarjano | Valdecy Pereira : Simulação de instrumentos musicais acústicos em tempo real utilizando redes neurais paralelas no domínio da frequência. Anais do XXXIX Encontro Nacional De Engenharia De Produção - ENEGEP, 2019. dx.doi.org/10.14488/ENEGEP2019_TN_STO_292_1654_37336.

Carlos Tarjano | Ruben Gutierrez | Valdecy Pereira : Traditional and alternative bibliometric indicators: assessing the evolution of interest in project management paradigms. Anais do XXXIX Encontro Nacional De Engenharia De Produção - ENEGEP, 2019. 2594-9713.

Carlos Tarjano : Redes neurais aplicadas à modelagem de instrumentos acústicos para síntese sonora em tempo real. Master's Degree Thesis - Production Engineering - Fluminense Federal University, 2018. dx.doi.org/10.22409/TPP.2018.m.11839251743. Available online(Portuguese).

Carlos Tarjano | Valdecy Pereira : Neural Networks as a Tool for Big Data: The State of the Art. Anais do I Simpósio Internacional de Network Science - SINS, 2017. networkscience.com.br/anais/.

Carlos Tarjano | Magda Leite | Paula Purcidonio : O Processo de Desenvolvimento de Produtos em Startups Baseadas em Inovação Criativa. Espacios. Vol. 37 (Nº 07). Pág. 6, 2016. 0798 1015.

bulb

PROJECTS

2023 - Piano Forte. Piano synthesiser based on a lightweight (~600KB, ~150k parameters) neural network and a novel representation for Quasi-Periodic signals..

2022 - Omnes Sonos. The first plugin to leverage neural networks to sound synthesis in real-time.

2022 - Harmonic Compression. Lossy compression codec based ond pseudo cycles segmentation. Registered in Brazil under the number BR512022000697-9.

2021 - Mark Book. Cross-platform songbook developed in Flutter. Available for Windows, Android and Web. Registered in Brazil under the numbers BR512022000618-9 BR512022000620-0.

2021 - Signal-envelope. A Python module to extract the envelope of digital signals. Registered in Brazil under the number BR512022000622-7.

2021 - BibRust. Bibliographic manager made in Rust. Registered in Brazil under the number BR512021000226-1.

2020 - Neural Piano. Neural networks based piano software. Registered in Brazil under the number BR512020001653-7.

2018 - SongB. A minimalist songbook app with chord detection, easy chord repositioning and optimized C++ code. Registered in Brazil under the number BR512020001654-5.

skills

SKILLS

AI

Machine Learning

Natural Language Processing (NLP)

Python

Pytorch

Natural Language Understanding (NLU)

Natural Language Generation (NLG)

LangChain Guidance

large language models (LLMs)

C++

JUCE NeMo-Guardrails

PostgreSQL

ONNX spaCy Dart/Flutter

Rust

Candle

JS/Html/CSS

Tensorflow

Keras

Blender

CGI

Data Science

Digital Signal Processing (DSP)

Real-Time Sound Synthesis

Product Development

Docker

CI/CD pipelines

Git/Gitlab (source code version control)