# Akshay Desai > Software Engineer at Applied Intuition Location: San Francisco Bay Area, United States Profile: https://flows.cv/akshaydesai Senior Software Engineer with expertise spanning behavior/motion planning, and applied Machine Learning for autonomous robotic systems. I architect and implement the core decision-making software that enables vehicles to navigate complex and dynamic real-world environments. My expertise fuses the precision of classical robotics, including trajectory planners , state machines , and feature arbitration, with advanced AI. I leverage machine learning and LLMs to solve critical challenges in root-cause analysis, system reliability, and virtual validation, creating more robust and intelligent autonomous solutions. Core Competencies: * Planning and Controls: Behavior Planning, Motion Planning, Trajectory Planning, Lane Level Map translation * AI & ML: Supervised and Unsupervised Machine Learning, Anomaly Detection, LLMs, Deep Learning * Tools: C++, Python, ROS, Linux, Simulators (Carla, CarMaker), CAN tools ## Work Experience ### Software Engineer, Behavior Planning @ Applied Intuition Jan 2026 – Present | Sunnyvale, California, United States ### Senior Software Engineer II, Autonomy @ Ford Motor Company Jan 2024 – Jan 2026 | Ann Arbor, MI • Worked on the Behavior Planner and Constraints Generation for highway features like merging, split-handling, tactical and mandatory lane changes. • Developed and deployed an LLM-based scene reasoning module that translated raw vehicle signals and image data into ranked root-cause analyses with explanatory narratives, improving the accuracy of traditional rule-based methods by 9 percent. • Applied supervised and unsupervised Machine Learning techniques on large-scale fleet data to predict root causes of BlueCruise system cancellation events, driving improved system reliability. • Designed and implemented an anomaly detection pipeline to identify novel, safety-critical events from production vehicle logs. • Re-factored the Behavior Selection module to handle stay-in-lane and lane change behaviors. ### Senior Software Engineer, Autonomy @ Ford Motor Company Jan 2021 – Jan 2024 | Ann Arbor, Michigan, United States L4 Autonomous Shuttle: • Created a remote route-request/take-over pipeline as part of the Autonomous Shuttle project to allow remote teleoperation of the AV shuttle • Enhanced the reliability of planning and decision-making algorithms to effectively handle intersections and start/end of route scenarios for the AV shuttle project. • Improved route and motion planner robustness by adding replanning logic to handle dynamic and uncertain environments. • Devised and demonstrated a business case prototype for autonomous parking of fully assembled vehicles in manufacturing plants. • Implemented a controlled safety stop-trajectory of the Autonomous vehicle when encountering specific failure criteria. • Led research collaborations with universities on aspects of Motion Planning C++ | Python | ROS | AOS | Jira | Agile | Carla Simulation ### Algorithm Engineer - ADAS (Magna & Lyft Collaboration) @ Magna International Jan 2019 – Jan 2021 | Troy, Michigan, United States • Collaborated on the development of a C++ Trajectory Planner and Controller library, which encompassed lateral features like Lane Keeping and Lateral Collision Avoidance. This involved integrating environmental signals, driver inputs, and vehicle states. • Constructed a C++ pipeline for Ethernet-based UDP communication on the dSpace Embedded PC, enabling real-time execution of C++ executables. This setup facilitated seamless interaction with the dSpace MicroAutoBox for Vehicle I/O data via CAN communication. • Utilized CAN tools (CANoe, CANalyzer, CANdb++, etc.) to capture and analyze CAN data for the integration of features such as Adaptive Cruise Control (ACC) and Traffic Jam Assist (TJA) into test vehicles. • Assisted in the development of the State Machine responsible for feature arbitration between various longitudinal and lateral functions, including ACC, Autonomous Emergency Braking (AEB), and Lane Centering. • Created CarMaker simulation environments to validate the performance of features such as ACC and TJA in diverse traffic and road scenarios. ### Software Engineering Intern - Autonomous L2/L3 @ Magna International Jan 2019 – Jan 2019 | Greater Detroit Area • Developing control strategies for path-tracking and deploying them on test vehicles using dSPACE solutions for prototyping and implementation. • Conducting research on planning algorithms for advanced driver assistance and semi-automated driving features like Adaptive Cruise Control and Traffic Jam Assist. • Using CAN tools (CANoe, CANalyzer, CANdb++, etc) to record, analyze and, manipulate CAN data for integration of features in test vehicles. • Using CarMaker simulation environment to validate the performance of Automated Driving features. • Using GIT and PTC for Version Control (Keeping track of model development, code update, and documentation). • Working on automation scripts for vehicle parameter characterization. • Built a simulation script to evaluate the Sensor Fusion algorithm by associating the Radar and Camera object data frames. • Worked on the Target Object Selection Algorithm based on the Ego Vehicle Path Prediction. ### Self Driving Cars Engineer Nanodegree @ Udacity Jan 2018 – Jan 2019 | Greenville, South Carolina Area • Project 1 - Path Planning : Created a local planner for the ego vehicle with a trajectory generation module. This was guided by the high-level behavior planner that assigned probabilities to the traffic behaviors. The local trajectories were evaluated based on cost functions. • Project 2 - Extended Kalman Filter : Implemented an Extended Kalman Filter to track a target object position using simulated Lidar and Radar data. • Project 3 - Unscented Kalman Filter : Implemented an Unscented Kalman Filter to track a target object position using simulated Lidar and Radar data. The Constant Turn Rate and Velocity model was used for the target object tracking. • Project 4 - Localization using Particle Filter : Implemented a 2-D particle filter in C++. This was accomplished using map data and sensor information to specific landmarks. • Project 5 - Model Predictive Control Project : Implemented an MPC that was able to track a planned route for the ego vehicle. This kind of control had to take factors such as control latency into account for the cost function. • Project 6 - Traffic Sign Classifier : Created a traffic sign classifier pipeline on Jupyter Notebook with a Deep Neural Network that was built in Tensorflow. This was able to achieve a validation accuracy of 96% and a test accuracy of 93.5% on a German traffic sign database. Concepts such as image normalization, L2 regularization, dropout, inception modules, and ReLu activations were used. • Project 7: Created an end to end Neural Network using Keras on Unity3D simulator track. Nvidia's Deep Neural Network was replicated to directly map image data to steering output for a simulated vehicle. • Project 8: Created an Advanced Lane Finding pipeline by extracting image features using techniques such as Sobel transforms (magnitude and direction) and Color Spaces (HLS, YUV). ### Introduction to Self Driving Cars Nanodegree @ Udacity Jan 2017 – Jan 2018 | Greenville, South Carolina Area • Project 1: Created a 2D Histogram filter over a discrete grid in the Spyder python editor. This could localize a robot based on the sense and move loop. • Project 2: Translated the 2D Histogram code from Python to C++ using Object Oriented Programming and optimized the code further, to reduce the compilation time. • Project 3: Implemented Data Structures based search algorithms to navigate from any start to goal position on an actual map of nodes. • Project 4: Obtained IMU and speed sensor values and created an algorithm to integrate and differentiate data in order to track the position and velocity of the vehicle at a given time step. • Project 5: Implemented a traffic light classifier by extracting different color spaces and determining the state of a traffic light with a test accuracy of 97 %. ### Autonomous Vehicle Software and Hardware Team - Deep Orange 10 @ Clemson University International Center for Automotive Research Jan 2017 – Jan 2018 | Greenville, South Carolina Area As a member of the esteemed Deep Orange Program at CU-ICAR, I worked on the following aspects of the Autonomous Software and Hardware team:- • Designed the software architecture for various autonomous functions, including valet parking, lane centering, and obstacle avoidance. A ROS-based architecture was implemented on the NVIDIA DRIVE PX2 platform, with a golf cart serving as the final test bed. • Implemented an IMU, wheel speed, and GPS based odometry model and tested it on a golf cart for low speeds. • Developed a comprehensive Motion Planning and Control pipeline for the implementation of autonomous parking, incorporating a Hybrid A* planner and Stanley Controller. • Assessed planning algorithms such as Hybrid A* and RRT (Dubins Path) in conjunction with a Pure-Pursuit/Stanley controller. Algorithm testing was conducted on GAZEBO using a kinematic vehicle model with ROS integration. • Supported in field of view analysis and sensor suite selection for the perception module, which integrated data from Velodyne Lidars, monocular cameras, stereo cameras, IMU, and high-precision GPS. ### Machine Learning @ Coursera Jan 2017 – Jan 2018 | Greenville, South Carolina Area • Implemented key concepts such as Linear, Logistic Regression, Gradient Descent, Neural Networks (forward and back propagation), and Anomaly detection without the use of libraries. • Completed projects on Linear Regression, Neural Networks, Unsupervised Learning, Large Scale Machine Learning, Anomaly Detection and Photo OCR (to recognize words, digits, and objects). ### Product Development Engineer at Ford Motor Company @ Ford Motor Company Jan 2016 – Jan 2017 | Chennai Area, India • Led the High Time in Service team for Steering, Wheels and Tires, to analyze and implement design changes based on warranty claims. This involved extensive data analysis, pattern recognition, root cause identification, excel VBA and Octave programming. • Supported Chassis integration team in the feasibility study for localization and bench-marking ideas. This was accomplished by analyzing customer behavior and predicting the future demands and market trends. • Received Recognition award from global Chassis Director for Design and Project management contribution for quick implementation of Tire design change on an On-going program through warranty data analysis. • Worked with the regional team to partially automate the work done by the systems integration division. The automation was accomplished through excel programming. ### Ford College Graduate at Ford Motor Company @ Ford Motor Company Jan 2015 – Jan 2015 | Chennai Area, India • Joined Ford as a College Graduate and was part of the FCG program which is a well-crafted transformation journey aimed at seamless transition from college to corporate. This program helped me apply engineering skills in a corporate environment and work with diverse groups. • Cross-Functional Training (CFT): Successfully reduced the "Exhaust system tooling cost" for an Asia Pacific program and reduced the labor cost over the product lifecycle by understanding the economics of compensation during my tenure with the Purchase division. The CFT was aimed at providing a broader outlook of the business operations. • Lead the Engaging Activities for the Ford Aspire Launch Campaign. • Gained a comprehensive understanding of the Ford manufacturing processes by being a part of the 4-week plant orientation. ### Automotive Industry Simulation Intern - Controls @ ExpertsHub Industry Skill Development Centre Jan 2014 – Jan 2014 | Chennai Area, India • Obtained insight into the design and functionality of modern propulsion systems. • Presented findings on remapping of turbocharger operating pressures to decrease turbo lag and increase top-end boost. • Received hands-on experience to dismantle and assemble various types of automotive engines • Gained insight into the latest research in automotive chassis and powertrain controls. ### Intern @ Alstom Jan 2014 – Jan 2014 | Andhra Pradesh, India • Project: " Optimization of Workflow and Process Distribution between Assembly Stations “. Presented the concept of an integrated plant monitoring system to ensure efficient workflow by displaying key information to the workers. Studied the stations to reduce NVA activities by employing "5S" and "Kaizen". • Gained comprehensive insight into the Components, Assembly Techniques and the Fail-Safe Systems involved in building the Chennai Metro Rail. ### Intern @ Renault Nissan Automotive India Pvt Ltd. Jan 2013 – Jan 2013 | Chennai Area, India • Gained insight into the large-scale applications of centralized monitoring systems in manufacturing and testing applications. • Project: "Reduction of Inventory through the study of the process flow using predictive approaches". Presented a report highlighting the probable bottlenecks and proposed methods to actively monitor and keep inventory levels to a minimum. ## Education ### Master's degree in Automotive Engineering Clemson University ### Bachelor's degree in Mechanical Engineering, First Class with Distinction, Mechanical Engineering College of Engineering, Guindy ### Senior Secondary Education Chettinad Vidyashram, R A Puram, Chennai ## Contact & Social - LinkedIn: https://linkedin.com/in/akshay-desai9 --- Source: https://flows.cv/akshaydesai JSON Resume: https://flows.cv/akshaydesai/resume.json Last updated: 2026-04-11