Tech stack, XR

Unity

Used in 9 places directly.

Projects (3)

HRIA: Romanian Artificial Intelligence Hub

AI Research Engineer, National University of Science and Technology POLITEHNICA Bucharest

From research prototype to production: training and evaluating ML/DL models, then building the CI/CD, infrastructure and MLOps workflows that run them reliably within Romania's national AI hub.

Design, train and evaluate machine-learning and deep-learning models; run experiments and iterate on architectures against research objectives.
Profile and optimise algorithms for accuracy, speed and resource efficiency, turning prototypes into clean, production-quality code.
Build CI/CD pipelines for ML workloads: automated tests, model validation, versioning and release workflows.

LLMsRAGPyTorchKubernetesGitLab CI/CD+14

Apr 2026 - Present

University ContractEU-fundedActive

Sound of Vision: audio-haptic navigation for the visually impaired

Software Developer & DevOps Engineer, PhD candidate, ACS-UPB

Real-time detection of obstacles, text, pedestrians and stairs rendered as spatial audio and wireless haptic feedback, running on a GPU-accelerated NVIDIA Jetson edge cluster orchestrated with Kubernetes and MLOps.

Detection algorithms for obstacles, text, pedestrians, sidewalks and elements of interest (stairs, doors, potholes) using deep-learning computer vision.
Spatial-audio rendering optimised so users can classify objects and navigate a scene by sound.
Designed the fully wireless haptic belt: wireless charging and ESP-NOW communication via an ESP32-C3, and the algorithms controlling haptic parameters.

KubernetesKubeflowTriton Inference ServerCUDAArgo CD+30

Apr 2024 - Present

University ContractEU-fundedActive

TRAVEE: VR neuro-rehabilitation platform

Software Developer with DevOps, ACS-UPB

Unity serious games fused with EEG, FES and haptic feedback, plus AI analytics, to accelerate post-stroke recovery in clinics and at home, with a full CI/CD and cloud backbone on AKS.

Built Unity (C#) mini-games for reach, balance, gait and coordination with OpenXR, Quest and Windows MR support.
Engineered data handlers synchronising EEG, FES and haptic streams into a state machine that auto-tunes difficulty from real-time performance metrics.
Modularised the Unity codebase into packages/ScriptableObjects; exposed REST and WebSocket APIs (ASP.NET Core) for profiles, session logs and remote progress; OAuth2/SAML auth and AES-256 encryption.