I am a Computer Science researcher with an M.S. from Texas State University.

My research focuses on:

• Neural Video Compression
• Computer Vision
• Edge AI
• Multimedia Systems
• Efficient Machine Learning

My master's research investigated ROI-aware video compression for resource-constrained wildlife monitoring systems, combining sparse animal detection, optical-flow tracking, motion-aware frame selection, and ROI/background compression.

I am also a co-author of an accepted IEEE ICTAI 2026 short paper on ROI-aware wildlife video compression and reconstruction.

Mykhailo Sakevych, Felix Mathew, and Vangelis Metsis

Accepted short paper,
38th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026)

The work investigates ROI-aware wildlife video compression across neural and conventional codec backends.

M.S. Thesis · Texas State University · Advisor: Dr. Vangelis Metsis

Developed an ROI-aware video compression framework for resource-constrained wildlife monitoring systems using sparse animal detection, KLT optical-flow tracking, motion-aware frame selection, and separate ROI/background compression.

At the selected thesis operating point, the system achieved a 97.40% reduction in transmitted archive size across 20 held-out wildlife clips while prioritizing visual quality in animal regions.

Technologies

PyTorch · Pytorch-Wildlife · MegaDetector V6 · OpenCV · KLT Optical Flow · DCVC-RT · FFmpeg · AV1 · HEVC · NVIDIA Jetson Orin Nano

Full thesis text is under institutional embargo until May 2027.

Research Software · PyTorch · CUDA/C++ · INT16 · rANS · FFmpeg

Developed a deterministic INT16 runtime adaptation for a DCVC-RT-family neural video codec to support reproducible edge-to-server neural video compression workflows.

The project includes:

• deterministic entropy-state handling
• rANS entropy coding
• encode/decode validation
• SHA-256 verification
• byte-level bitstream comparison
• CUDA/C++ runtime integration

A same-environment validation produced identical SHA-256 hashes and byte-for-byte identical bitstreams across repeated runs.

Graduate Research Assistant
Jan. 2025 – May 2026 · San Marcos, Texas

• Conducted research in computer vision, neural video compression, and edge AI.
• Developed and evaluated an ROI-aware wildlife video compression framework.
• Worked with neural and conventional video codecs under edge-computing constraints.

Graduate Instructional Assistant → Graduate Teaching Assistant
Jan. 2025 – Jun. 2026 · San Marcos, Texas

• Led CS 1428 laboratory sessions covering C++, pointers, dynamic memory, object-oriented programming, debugging, and introductory data structures.
• Supported grading coordination and instruction for a large introductory programming course serving more than 500 students.

Associate Software Engineer
Aug. 2021 – Jan. 2023 · Mumbai, India

• Developed backend and full-stack components for production applications using AWS, relational databases, REST APIs, and event-driven architectures.
• Built AWS Lambda-based services and tenant-isolated workflows with MySQL, including idempotent processing and transaction-safe data recovery procedures.

Master of Science in Computer Science
Aug. 2024 – May 2026
GPA: 3.56 / 4.00

Thesis:
Neural Region-of-Interest-Aware Video Compression for Wildlife Monitoring Under Edge Computing Constraints

Advisor: Dr. Vangelis Metsis

Bachelor of Technology in Computer Science and Engineering
Jun. 2018 – Jun. 2021
CGPA: 8.56 / 10

• Graduate Merit Fellowship, Texas State University, 2024–2025
• CodePath AI Open Source Capstone — Honors
• AWS Certified Generative AI Developer — Professional
• AWS Certified Solutions Architect — Associate