Mobile Security Researcher — Android Malware Detection & Applied ML
I'm a mobile application engineer with 6+ years of experience shipping 35+ Android and Flutter applications across healthcare, logistics, e-commerce, and industrial sectors, now completing an MSc in Cyber Security at Sheffield Hallam University (expected September 2026). My dissertation applies machine learning to Android malware detection, and I'm growing my background in AI/ML tooling and secure coding practices alongside it. I'm looking for a fully funded doctoral position in Europe to take this research further — into adversarial robustness, on-device ML security, or applied mobile-security research more broadly.
Sheffield, UK · jayesh17296@gmail.com · +44 7344405498 · GitHub · LinkedIn · Stack Overflow · Medium
Over six years I've designed, developed, and launched 35+ mobile applications across healthcare, logistics, e-commerce, and industrial sectors, working in Kotlin, Java, Flutter, and Firebase, and building a growing base in AI/ML tooling (TensorFlow, MediaPipe, ARCore). I've worked across the full software development lifecycle in Agile teams, mentored junior developers, and contributed to open-source and technical writing communities. That engineering background is what pulled me toward security: the more systems I shipped, the more I wanted to understand how they're attacked, and how to build detection into them from the ground up.
I'm now completing an MSc in Cyber Security at Sheffield Hallam University (expected September 2026), and I'm ISO/IEC 27001 certified. My dissertation focuses on machine-learning-based Android malware detection. I want to continue this as doctoral research — combining hands-on mobile engineering experience with rigorous, reproducible security research — and I'm actively seeking fully funded PhD positions in continental Europe.
Areas I'd like to pursue further as a doctoral researcher.
Machine-learning classifiers for identifying malicious Android applications from static and behavioural features.
Balancing detection accuracy against inference time and model size for practical, on-device deployment.
OWASP Mobile Top 10, reverse-engineering resistance, and secure coding practices for mobile applications.
Integrating machine learning models into real mobile applications, informed by production engineering experience.
Trained and evaluated machine learning classifiers on a curated dataset of 16,453 Android application samples with 810 extracted features, to identify models that are Pareto-optimal across detection performance and computational efficiency. Linear SVM and Logistic Regression emerged as the strongest trade-off points, with the Linear SVM achieving high detection accuracy at a fraction of the inference cost — making it suitable for on-device deployment. The findings are demonstrated in a companion Android application built in Kotlin and Jetpack Compose.
Dissertation on ML-based Android malware detection under the supervision of Dr. Mark Jacobi, alongside coursework in penetration testing, secure software development, cryptography, and network security.
Foundation in computer science fundamentals, software engineering, data structures, and algorithms, with early project work in mobile application development.
The engineering practice that grounds my security research.
Led Flutter development across multiple concurrent production projects end-to-end. Delivered Seabird Cargo Terminal (enterprise logistics, MVVM + GetX), PC Fitment, MR Divine Savior (B2B industrial catalog), Crane Management App, SURI Agro Fresh (real-time delivery tracking), and Candy Bomb Blast (published Android game). Implemented secure API integrations and role-based access control, reviewed and refactored team code for performance and stability, and mentored junior developers on clean code and debugging.
Developed and optimised Android applications for the diamond industry, including RFID and device scanner apps for inventory and security management, and SuraSole Medical — a wearable IoT insole system for remote rehabilitation monitoring, gait/balance tracking, and fall alerts. Integrated third-party APIs, implemented secure data storage, and fixed security-related bugs and logic flaws.
Built Android applications in Kotlin and Java, including the Giffi Texy Driver App (logistics/transportation) and the Uflyp Amazon Mediator App (e-commerce integration). Implemented API integrations and authentication workflows, gaining hands-on experience in debugging, testing, and secure coding fundamentals.
Completed professional training in Android application development using Java and Kotlin, building multiple applications covering UI design, APIs, debugging, and deployment.
Assembled, repaired, and maintained computer systems, peripherals, and networking equipment; installed operating systems and software; assisted with CCTV installation and basic security device configuration.
Enterprise logistics application built at OMEX Infotech using MVVM architecture and GetX state management.
Mobile extension of a fitment data tool enabling auto parts sellers to submit accurate data to Amazon, eBay, Walmart, and other marketplaces.
Smart insole system using wearable sensors and IoT to remotely monitor rehabilitation progress, track balance and walking data, and alert caregivers to falls.
A mindfulness app with guided audio sessions, offline support, secure local data handling, and a custom background-playback audio player.
Flutter-based industrial management solution for crane operations, scheduling, and maintenance tracking, with GPS tracking and role-based access control.
MSc dissertation project: ML classifiers for Android malware detection, evaluated for the Pareto-optimal trade-off between accuracy and computational cost, with a companion Kotlin/Jetpack Compose app.
46 technical articles published on Medium, with 2 more scheduled — covering mobile development, applied AI/ML, and security. Selected highlights below; full archive on Medium.
Reach out about doctoral research opportunities, collaborations, or my dissertation work.