
Dimitris Lillis
@dimitrislillis
ML and computer vision engineer at DUTH, comparing EfficientNet, DINOv2 and BiomedCLIP for melanoma detection.
What I'm looking for
At Democritus University of Thrace, I compared EfficientNet, DINOv2 and BiomedCLIP for melanoma detection on dermoscopy images. Using lesion-level splits to avoid data leakage, I found that tuning the decision threshold—not changing the backbone—gave the biggest gain: about 81% melanoma recall at 0.36 precision. I treat the model as a screening aid, not a diagnostic tool.
My work spans hardware and software, from IoT systems and PCB design to Python ML pipelines and LLM-integrated web apps. I completed an R&D internship at Sunlight Group focused on BMS and energy storage systems, and contributed to Formula Student DUTH’s Low Voltage systems. I’m available from May 2027 for ML, computer vision or AI roles.
Experience
Work history, roles, and key accomplishments
Military Service
Hellenic Army
Nov 2026 - Present (0 months)
Worked as Military Service at Hellenic Army.
Research And Development Engineer Intern
Sunlight Group
Jul 2025 - Aug 2025 (1 month)
Worked as Research And Development Engineer Intern at Sunlight Group.
Education
Degrees, certifications, and relevant coursework
Democritus University of Thrace - (D.U.Th.)
Master's Degree, Electrical and Computer Engineering
2021 - 2026
Availability
Location
Authorized to work in
Salary expectations
Social media
Job categories
Skills
Interested in hiring Dimitris?
You can contact Dimitris and 600K+ other talented remote workers on Himalayas.
Message DimitrisGet matched with your dream remote job
Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
