Carlos Henrique Tarjano Santos, PhD

• tarjano@live.com
• github.com/tesserato
• linkedin.com/in/carlostarjano
• orcid.org/0000-0003-3134-2778

Machine Learning Engineer | Researcher (PhD) building production-grade AI systems, ranging from bespoke neural architectures in low-level languages to multi-agent LLM workflows (local and API-based). My work spans real-time neural audio systems, automated feature engineering, feature stores, synthetic data generation, digital signal processing, and reproducible ML infrastructure for energy platforms.

Experience includes a strong research track record (140+ citations, €330K+ in funding), open-source contributions (700+ stars, 5K+ users), and work across startups, industry (400+ B2B users), and research labs, with hands-on software engineering in Python, Rust, Go, and C++.

WORK

INESC TEC

Researcher at the Centre for Power and Energy Systems (CPES) (15/01/2024 - Present)

Within the ATE energy-transition consortium, a Portuguese agenda mobilizing 50+ companies and 20+ R&D institutions around a EUR250M+ innovation portfolio:

• led the architecture and development of Voltus, the feature store for CLOUDIA4.eu, a digital AI platform for energy-sector data and services
• Designed and implemented an LLM-driven multi-agent system for automated feature engineering that analyzes relevant state-of-the-art literature, use-case descriptions, and data samples to generate production-ready Python feature implementations, both for integration with Voltus and for standalone use

Within the AI-EFFECT, a Horizon Europe Testing and Experimentation Facility for energy AI spanning 19 organisations across Europe, including TU Delft, Fraunhofer, DTU, ENEL, and TenneT:

• Led the implementation of synthetic multivariate time-series generation services
• Designed and implemented core services and practices for the Portuguese node, including a stateless feature engineering server, a data server, and reproducible ML workflows for secure energy-AI experimentation

Introduced MLOps practices, established structured experimentation, and mentored junior researchers

Participated in conferences and workshops, presenting research and engaging with the scientific community

Match<IT>

Head of AI & Applied Research (NLP / GenAI) (17/03/2023 - 15/01/2024)

• Led the company’s AI/NLP strategy across research and production systems, aligning applied R&D with product delivery, enabling the company’s expansion into complex client environments across finance, education, and innovation ecosystems, strengthening offerings for large organizations, public-sector programs, and SME-focused platforms such as YDUQS (one of the largest higher-education groups in Brazil, 1.3M+ students), CAIXA (one of Brazil’s largest public banks, present in 99%+ of municipalities), SEBRAE Minas (a major regional SME support institution in Brazil), ANBIMA (the main Brazilian capital-markets association), and CEIA/UFG (a leading Brazilian AI research and innovation center with 1,000+ collaborators)
• Led and mentored a multidisciplinary team of 15 researchers and developers, overseeing hiring, roadmapping, execution, and cross-functional delivery
• Helped secure and manage funded R&D projects, including successful FAPESP PIPE proposals spanning €300K+ across two phases and the creation of 5 research positions
• Directed the transition of experimental NLP and GenAI systems into deployed B2B products, including a virtual innovation assistant used by 400+ companies and supplier-buyer matching workflows used by 200+ companies

AI / NLP Researcher (24/10/2022 - 17/03/2023)

• Designed and implemented production NLP and similarity algorithms to match technology suppliers and buyers using structured and unstructured data
• Applied neural networks and modern NLP techniques to improve relevance, scalability, and robustness in B2B matching pipelines
• Contributed directly to production-facing systems at the intersection of applied research, workflow automation, and real-world client delivery

Omnes Sonos

AI Audio Systems Engineer (ML / DSP, Real-Time Synthesis) (15/05/2017 - 24/10/2022)

Independent project on AI-based real-time sound synthesis, building on MSc and PhD research, integrating machine learning with digital signal processing to develop production-ready virtual instruments and plugins in close proximity with users and the community, balancing technical innovation with practical user needs.

• Researched and implemented neural architectures for real-time sound synthesis and audio representation learning, designed for low-latency / real-time constraints suitable for plugin environments
• Developed Piano Forte, an open-source piano instrument combining lightweight neural networks, physical modelling, and traditional DSP
• Released work publicly and engaged with the sound synthesis community; project outputs were featured by outlets such as Synthtopia, Sonicstate, Bedroom Producers and Rekkerd

UFRJ (Federal University of Rio de Janeiro)

Academic Operations Officer (27/01/2009 - 15/05/2017)

Tenured federal position obtained through a highly competitive national selection process, where I operated across multiple institutional roles within one of the largest universities in Latin America, combining administrative leadership, data analysis, and process automation:

• Implementation and management of the International Relations undergraduate program
  
• End-to-end management of the Philosophy graduate program
  
• Served as vice-chief of the IFCS financial center
  
• Led and supported digital transformation initiatives, including workflow automation, document digitalization, and the implementation of internal information systems
• Designed analytical tools to assess academic performance and scholarly production

EDUCATION

PhD in Industrial Engineering and Management (Portuguese recognition of foreign degree, 320240067419) U.PORTO (Porto University) (07/03/2024)

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

Visiting Research Fellow at ICCMR (Interdisciplinary Centre for Computer Music Research) University of Plymouth (01/01/2020 - 31/03/2020) where I developed research on the interface between machine learning and real-time sound synthesis under the supervision of Eduardo Reck Miranda

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)

PROJECTS

2026 - Tect. Declarative programming language for architecture-as-code.

2026 - Scatters. Interactive, single-file HTML plots from data and audio.

2025 - CodeWeaver. CLI tool for converting codebases into LLM-ready Markdown.

2025 - Inscribe. Markdown preprocessor that executes embedded code.

2025 - CloudMapper. CLI to map and visualize cloud storage.

2024 - Dead Simple Blog Generator. Static websites from Markdown and HTML directories.

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

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

2021 - Signal-envelope. A Python/C++ 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-network-based piano software. Registered in Brazil under the number BR512020001653-7.

2018 - SongB. Songbook with chord detection, chord repositioning and optimized C++ code. Registered in Brazil under the number BR512020001654-5.

PUBLICATIONS

Valdecy Pereira | Marcio Basilio | Carlos Tarjano: Enhancing decision analysis with a large language model: pyDecision, a comprehensive library of MCDA methods in Python. Journal of Modelling in Management, August 2025. doi.org/10.1108/JM2-04-2024-0118.

Valdecy Pereira | Marcio Basilio | Carlos Tarjano: PyBibX - a Python library for bibliometric and scientometric analysis powered with artificial intelligence tools. Data Technologies and Applications, Volume 59, Issue 2, January 2025. doi.org/10.1108/DTA-08-2023-0461.

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: Signal-Envelope: A C++ library with Python bindings for temporal envelope estimation. arXiv, October 2021. doi.org/10.48550/arXiv.2110.11807.

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.

PEER REVIEW

Served as a peer reviewer for journals including EURASIP Journal on Audio, Speech and Music Processing, Journal of Informetrics and Technology in Society. See ORCID for details.

MISCELLANEOUS

2025 - Conference. Energy Technology Open Day. Presentation: Language Models for Automatic Feature Engineering. Porto, FEUP (October 15th).

2025 - Conference. Conferência ATE: Liderar a mudança: soluções para um novo paradigma energético. Stand showcasing the CLOUDIA4.eu platform MVP, the Voltus Feature Store, and synthetic time series generation results. I was particularly responsible for the Voltus Feature Store. Porto, Super Bock Arena (June 26th).

2025 - Blog. The Fortnightly Tambourine. A blog aimed at popularizing science.

2023 - Competition. Neural Audio Plugin Competition. Organized by The Audio Programmer and Neutone. Presentation of the Piano Forte project.

2023 - Funding. Auxílio à Pesquisa - Pesquisa Inovativa em Pequenas Empresas - PIPE. Preparation of a successful funding proposal for the Brazilian agency FAPESP, securing total funding of R$ 1.000.000,00 (approximately 160.000 euros). More details at orcid/funding.

2023 - Interview. Adeus aos longos formulários: como especificar projetos com conversas simples. Interview as Match<IT> Head of Data about conversational agents.

2019 - Conference. XXXIX Encontro Nacional de Engenharia de Produção (ENEGEP). Oral presentation of the paper “Simulação de instrumentos musicais acústicos em tempo real utilizando redes neurais paralelas no domínio da frequência”.

2019 - Conference. XXXIX Encontro Nacional de Engenharia de Produção (ENEGEP). Oral presentation of the paper “Traditional and alternative bibliometric indicators: assessing the evolution of interest in project management paradigms”.

2017 - Conference. I Simpósio Internacional de Network Science (SINS). Oral presentation of the paper “Neural Networks as a Tool for Big Data: The State of the Art”.

2014 - Crowdfunding campaign. Carcara Eco Footwear. Crowdfunding campaign for a line of eco-friendly shoes.

SKILLS