Leonardo Leon Vera

ML/CV Engineer with 7+ years building and deploying real-time video analytics and production AI systems on AWS and GCP. End-to-end ownership from model training (PyTorch, YOLO, pose estimation) through serverless and GPU-optimized inference (ONNX, TensorRT, Lambda, SageMaker). Specialized in low-latency streaming pipelines and Vision-Language Models (VLMs) for multimodal visual understanding at production scale.

Computer Vision & Machine Learning Engineer at LEN (2026-02 – Present)

• Designed and deployed a scalable end-to-end computer vision pipeline on Amazon Web Services using AWS Step Functions, AWS Lambda, Amazon SageMaker Batch Transform, and Amazon DynamoDB for production-scale sneaker analysis
• Developed a multi-stage ML/CV pipeline with person detection, custom PyTorch sneaker segmentation, and FAISS embedding-based sneaker brand/model classification
• Built modular serverless inference services with one Lambda per model to improve scalability, maintainability, and parallel processing
• Optimized the pipeline for high-throughput processing of 10k+ images, reducing inference time and infrastructure costs in production

Computer Vision & Machine Learning Engineer at ShotQuality (2024-07 – 2025-12)

• Designed and deployed real-time computer vision pipelines for basketball analytics using AWS and GCP
• Developed 2D and temporal models for detection and pose estimation on live video streams
• Reduced inference latency by using ONNX optimization and GPU acceleration
• Built scalable infrastructure with automatic vertical scaling for handling live streaming workloads
• Built and deployed multimodal systems using Vision-Language Models (VLMs) for OCR and visual understanding tasks

AI Tech Leader, Computer Vision at Atos & Eviden (2021-06 – 2024-06)

Developing Computer Vision projects using MLOps tools in a Big Data team

• Led development of large-scale computer vision systems in a retail environments using multi-cameras
• Trained and deployed models using NVIDIA TAO and DeepStream for high-performance inference for +20K cameras in a big smart-city project
• Converted models (Keras/YOLO ONNX TensorRT) for production deployment in local servers
• Managed multi-GPU training pipelines for medium and large-scale datasets

AI Tech Leader (Part-time) at CTIC - UNI (2022-08 – 2023-08)

• Lead Smart City AI initiatives: face recognition, license plate detection, and smart parking for university deployments
• Deliver real-time inference pipelines with Docker and GPU-based systems for on-premise production environments
• Design scalable on-premise architectures supporting 10+ concurrent video streamings in limited resources

Computer Vision & Machine Learning Engineer at Dod & Getter AI (2019-04 – 2021-12)

Leading and developing projects of Machine Learning and Computer Vision for Education, Retail, Ergonomics 4.0 using open source Deep Learning frameworks from collecting data to deployment with API

• In other one for a PUCPR university we implemented a face expression, gaze estimation and people recognition system in order to measure attention and students' emotions in a classroom

M.S. in Informatics, AI Specialization – Pontifical Catholic University of Paraná (2021 – 2024)

B.S. in Computer Science – Universidad Nacional de Ingeniería (UNI) (2013 – 2018)