Mayank Phular

Highly analytical Senior System Engineer with over 7 years of experience in ADAS radar perception, algorithm development, system testing and embedded system validation within the automotive domain. Demonstrates strong expertise in radar object detection, Sensor Fusion architectures, RTOS-based embedded systems, and algorithm optimization supporting L2/L3 autonomous driving systems. Proven expertise in System Testing, radar validation frameworks (SIL/HIL/PIL), and the complete Software Development Lifecycle (SDLC) across complex automotive programs, serves as a Certified Scrum Master with a proven track record of leading Agile teams to deliver complex, safety-critical ADAS solutions.

Technical Specialist (Radar Detection & Tracking) at Continental Automotive India Pvt Ltd. (2022-04 – Present)

• Architected a Radar Ambiguity Resolver Framework for dSPACE synthetic recordings supporting GM and Ford platforms, significantly improving radar data fidelity and earning direct customer recognition following successful deployment.
• Developed advanced radar detection and tracking algorithms supporting L2/L3 ADAS functionality, elevating algorithm test KPIs from 65% to 93% accuracy.
• Engineered a Gen6 radar object tracking validation platform and contributed over 40% of the core reference dataset, strengthening detection reliability and system verification capability.
• Executed end-to-end validation for Short Range Radar (SRR) and Long-Range Radar (LRR) systems supporting Blind Spot Detection (BSD) and Adaptive Cruise Control (ACC) functionality.
• Designed a static mass detection concept for SRR630 radar, significantly improving object classification during production validation cycles and reducing BSD false positives by over 80%.
• Radar Ambiguity Resolver Framework (GM & Aurora): Designed and implemented a lightweight Radar Ambiguity Resolver Framework for dSPACE synthetic recording, improving system latency and reducing memory consumption by 20% while ensuring high data fidelity.
• Diagnosed and resolved complex software stability issues using Software-in-the-Loop (SIL) simulations and advanced debugging tools including Lauterbach TRACE32 and Hardware-in-the-Loop (HIL) platforms.
• Stabilized radar algorithms and improved runtime robustness, enabling timely delivery of customer software releases under strict delivery timelines.
• Led large-scale KPI validation for the Emergency Brake Assist (EBA) function by processing and analyzing 32,000+ km of fleet test data through an AWS-based data processing pipeline.
• Directed the full software development lifecycle including design documentation, unit testing using Google Test, and static code analysis using QAC Helix to ensure MISRA C-compliant, production-grade code quality aligned with ISO 26262 functional safety requirements.
• Optimized radar software performance and runtime stability through targeted debugging, system tuning, and continuous algorithm refinement.
• Facilitated Agile development as Scrum Master, coordinating cross-functional teams, resolving technical blockers, and ensuring milestone delivery across radar development programs.

Senior Analysis Engineer at Randstad India Pvt Ltd (Client: Continental Automotive) (2018-07 – 2022-04)

• Performed Radar Cross Section (RCS) measurements and radar target simulator calibration within controlled anechoic chamber environments to validate radar sensing performance.
• Collaborated with perception engineering teams to identify and eliminate false detections caused by multipath interference and environmental clutter.
• Validated radar hardware-software integration through rigorous development testing of core perception modules and system interfaces.
• Investigated complex radar software issues using Software-in-the-Loop (SIL) simulations and advanced debugging tools including Lauterbach TRACE32 and Hardware-in-the-Loop (HIL) platforms.
• Developed an AI-driven synthetic radar data generation framework to simulate radar scenarios, significantly reducing dependence on expensive field test data collection.
• Accelerated validation cycles by enabling rapid low-cost scenario generation, improving testing efficiency and minimizing reliance on costly fleet or chamber data acquisition.
• Stabilized radar object representation during Daimler Driving Function (DF) demonstrations by implementing algorithmic corrections that improved object tracking stability and classification accuracy under real-world driving conditions.
• Validated Emergency Brake Assist (EBA) performance by analyzing 32,000+ km of fleet data through a scalable AWS analytics pipeline, resolving critical inconsistencies in object dimension estimation and strengthening system KPI maturity.

B. Tech in Computer Science Engineering – Dehradun Institute of Technology (2016)