# Amirmasoud Ghasemi > ML Engineer at Coupang | Agentic AI | Large Vision-Language Models | MLOps | Robotics Location: San Francisco Bay Area, United States Profile: https://flows.cv/amirmasoud ## Work Experience ### Staff Machine Learning Engineer @ Coupang Jan 2024 – Present | Mountain View, California, United States - Led development of next-gen search experience leveraging agentic LLMs, Retrieval-Augmented Generation (RAG), and multi-step reasoning orchestration - Tech lead for computer vision and multimodal research - Designing and optimizing generative models to enhance product image quality through advanced image synthesis and restoration techniques. - Developing multimodal large-scale models to accurately predict product attributes and identify mismatches and policy non-compliance in listings. ### MLOps Team Lead @ DarkVision Jan 2022 – Jan 2024 | North Vancouver, British Columbia, Canada - Working with petabyte-size video dataset and deploying scalable computer vision solutions in the production environment (PyTorch, AWS Sagemaker, S3, EFS, relational DB, and container registry) - Created ETL and staging pipeline for measuring the performance of ML models at scale (Kubeflow, Prefect, Kubernetes, EKS, AWS Batch, Lambda, and Terraform) - Developed a real-time visual search engine dashboard and API service for exploring millions of ultrasound images using KNN and vector database (Amazon OpenSearch, Beanstalk, Plotly) - Setting up a workflow for model experiment tracking and model unit-testing using Data Version Control (DVC), Weights&Biases, and Kolena platforms ### Staff Software Engineer @ Nuro Jan 2022 – Jan 2022 - Developed production-level onboard C++ module to detect stuck circumstances - Scripted unit tests, checked the module performance on simulation, bench, and field vehicle, and finally deployed the module for the release ### Co-Founder @ Ladybug Robotics Jan 2021 – Jan 2022 • Led the engineering team with agile practices to build a robot for vineyard winter pruning and pilot it at the customer’s site The projects that have been accomplished under my supervision: • Utilized Google Cloud Platform (GCP) for model training and prediction • Simulated a virtual vineyard in Blender and generated synthetic data for pre-training and data augmentation • Applied supervised transfer learning and retrained Mask-RCNN, U-NET, and MMRotate for segmentation of highly overlapping branches (PyTorch) • Filtered and manipulated pointclouds in Open3D, registered pointclouds from multiple viewpoints using ICP and RANSAC optimization • Evaluated the accuracy of stereo depth estimation from OpenCV block matching, HITNet, and CREstereo on the synthetic dataset • Simulated robot’s manipulation in ROS and benchmarked +10 trajectory planners from MoveIt package • Integrated, calibrated, and tested ZED2i, RealSense D435i, Analog Device ToF, Occipital, and Leopard WDR Camera for outdoor sensing and data record • Developed React-based teleoperation dashboard and utilized roslibjs and WebRTC to stream real-time video from the robot and transfer messages between the robot and teleop dashboard through WebSocket and P2P communication ### Chief Technology Officer @ Tellext Jan 2020 – Jan 2021 | Vancouver, British Columbia, Canada • Successfully demonstrated a prototype of an autonomous security robot in a real environment (parking lot) for potential customers and investors • Developed a real-time ROS node for license plate recognition • Tested Facebook’s action recognition deep network (SlowFast) for suspicious behavior recognition on the collected data from the field • Implemented speech-to-text feature to detect suspicious keywords inside the conversations • Applied HDL Graph SLAM and created 3D map and localized robot using 3D lidar, wheel odometry • Tuned global and local ROS planners for autonomous navigation of the robot • Experimented and evaluated Autoware’s vector map for autonomous navigation inside the parking lots • Distributed computation between edge devices and running real-time object detection (Yolo), license plate recognition network, and navigation stack in parallel • Set up Webviz for remote monitoring of the robot ### R&D Manager @ Advanced Intelligent Systems Inc. Jan 2018 – Jan 2020 | Vancouver, Canada Area AIS's GreenUGV is for agricultural use and is to tackle challenges that greenhouse nurseries face in terms of reducing labor costs and increasing throughput, quality, and safety. • Was accountable for prioritizing and addressing the technological challenges from the ideation phase up to production in ongoing projects • Segmented and clustered lidar pointcloud for plant pot detection • Modified Hungarian optimization algorithm and created a multi-object tracker for real-time tracking of plant pots • Fused 2D and 3D lidars, visual odometry, UWB, and semantic objects to localize the robot with cm-level accuracy at the indoor greenhouse ### Research Program Director @ CAST (Center of Advanced Systems and Technologies) Jan 2012 – Jan 2015 | Tehran, Iran • Delivered an operational 190cm humanoid robot with 31 DoF in 3 years (video) • Communicated and reported the progress of the project to the internal and external stakeholders • Formed and organized a large team of 70 researchers and engineers in a matrix structure • Identified bottlenecks, unblocked process, and developed end-to-end plans for the project scopes ### Team Lead, Dynamics and Control @ CAST (Center of Advanced Systems and Technologies) Jan 2010 – Jan 2012 | Tehran, Iran • Supervised a group of 12 engineers and students, set goals, run sprints, and held daily meetings • Owned accountability for kinematics modeling, simulation, and motion control of active R&D projects (exoskeleton and humanoid robot) ### Robotics Engineer @ CAST (Center of Advanced Systems and Technologies) Jan 2008 – Jan 2010 | Tehran Province, Iran • Engaged in multiple robotic projects including fish-like swimming robot and humanoid robot SurenaII as a motion-control engineer • Experimented with different actuation systems (DC, AC, servo) and sensors (pressure sensor, camera, encoder) and developed fuzzy, optimal, and robust closed-loop controllers for robotics applications in Matlab and LabVIEW ## Education ### Master of Science - MS in Computer Science Simon Fraser University Jan 2017 – Jan 2021 ### Invention to Innovation Certificate Beedie School of Business at Simon Fraser University Jan 2020 – Jan 2021 ### Master of Science (M.Sc) in Mechatronics, Robotics, and Automation Engineering University of Tehran Jan 2011 – Jan 2014 ### Selctive courses on Master of Business Administration (MBA) University of Tehran Jan 2012 – Jan 2013 ### Bachelor of Science (B.Sc) in Mechatronics, Robotics, and Automation Engineering University of Tehran Jan 2007 – Jan 2011 ## Contact & Social - LinkedIn: https://linkedin.com/in/amirmasoud-ghasemi - Website: https://www.youtube.com/channel/UC1ZrUGG5BKFpx1j-4fROrBw/videos --- Source: https://flows.cv/amirmasoud JSON Resume: https://flows.cv/amirmasoud/resume.json Last updated: 2026-03-22