Software Engineer with 10+ years in C++ development for automotive systems. Specializing in embedded software, ADAS features, and AI-driven engineering solutions.
With over 10 years of professional experience in C++ development within the automotive industry, I've worked on complex systems across various organizational environments — from small agile teams to large enterprise setups.
My expertise spans embedded systems, real-time control software, and ADAS feature development. I'm particularly passionate about applying AI to real-world engineering problems and continuously expanding my technical leadership capabilities.
Currently focused on bridging the gap between traditional automotive software and modern AI-driven development workflows.
Preparing for Certified Associate in Project Management to strengthen technical leadership and project delivery capabilities. Building structured approaches to complex engineering projects.
Exploring Model Context Protocol (MCP) servers to integrate AI assistants effectively into development workflows. Focused on automating documentation, code review, and system analysis tasks.
Deepening expertise in Advanced Driver Assistance Systems, working with sensor fusion, computer vision, and safety-critical software architectures for next-generation vehicles.
Developed real-time lane detection and tracking algorithm for Level 2 autonomous driving features. Implemented sensor fusion between camera and LiDAR data for robust performance in varying weather conditions.
Key Achievement: Reduced false positive rate by 35% through advanced filtering algorithms.
Designed and implemented embedded control software for engine management ECU. Developed real-time scheduling algorithms and diagnostic protocols compliant with AUTOSAR standards.
Key Achievement: Achieved ASIL-D safety rating through rigorous testing and code coverage analysis.
Built comprehensive diagnostics and telemetry platform for fleet management. Created backend services for real-time data ingestion and web-based visualization dashboard for maintenance teams.
Key Achievement: Reduced diagnostic time by 60% through predictive maintenance algorithms.
Developed internal tool leveraging LLMs to automate code review processes for automotive software. Integrated with existing CI/CD pipeline to catch potential bugs and compliance issues early.
Key Achievement: Reduced review cycle time by 40% while maintaining code quality standards.