Skip to main content
Δημοσθένης Ελμάς
Open to opportunities

Δημοσθένης Ελμάς

@0007479

AI/ML engineer developing LLM and RAG tools in C++ and adapting Transformer and diffusion models for wind-farm forecasting.

Greece
Message

What I'm looking for

I’m applying to join Imnoo and would welcome the chance to help build its agentic AI tools and the infrastructure behind them.

At CERTH-ITI, I developed web and mobile applications and built APIs for database transactions and user authentication. I also co-authored two peer-reviewed papers on social-robot-based platforms for diet tracking and childhood-obesity prevention.

For my MSc thesis at Aristotle University of Thessaloniki, I adapted PyTorch implementations of the Informer, Temporal Fusion Transformer, and CSDI diffusion model to forecast wind-farm power output. I modified attention and training procedures and designed a multi-stage training scheme.

In my free time, I’m building a local RAG assistant in C++ with a FAISS index, ONNX Runtime embeddings, and a quantized LLM served through llama.cpp. It’s designed to run without a dedicated GPU and includes multi-turn conversation memory.

I’m also experimenting with a Unity-based tri-dexel machining simulation and reinforcement-learning environment with G-code support. Alongside that project, I’m collaborating with clinical doctors on statistical shape modeling of 3D medical volumes for a research publication.

Experience

Work history, roles, and key accomplishments

IC

Research Assistant

Information Technologies Institute (CERTH-ITI)

Feb 2018 - Aug 2020 (2 years 6 months)

Developed web and mobile applications for research projects using Angular, JavaScript/TypeScript, and Apache Cordova. Built web APIs handling database transactions and user authentication, and co-authored two peer-reviewed papers.

Education

Degrees, certifications, and relevant coursework

Aristotle University of Thessaloniki logoAT

Aristotle University of Thessaloniki

MSc, Artificial Intelligence

Grade: 9.21/10

MSc in Artificial Intelligence with grade 9.21/10. Thesis on forecasting renewable energy generation using deep learning.

University of Macedonia logoUM

University of Macedonia

BSc, Applied Informatics

Grade: 8.26/10

BSc in Applied Informatics with grade 8.26/10, top 6.9% of graduates.

Interested in hiring Δημοσθένης?

You can contact Δημοσθένης and 90k+ other talented remote workers on Himalayas.

Message Δημοσθένης

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan