Role Overview
The Machine Learning Team Lead position at Berry AI (Berry AI) is a full-time engineering leadership opportunity based in Taipei - Neihu, with remote work flexibility available. This role suits an experienced machine learning professional with a passion for guiding technical direction while remaining hands-on with cutting-edge computer vision systems deployed in thousands of real-world locations.
Key Responsibilities
Lead, grow, and mentor the machine learning and computer vision team, including overseeing technical direction, execution quality, delivery, and hiring.
Own the core computer vision capabilities behind the product, such as object detection, multi-object tracking, person and vehicle re-identification, camera calibration, geometric vision, and event recognition.
Collaborate with the Product department to translate customer challenges into clearly defined machine learning problems with actionable roadmaps.
Manage the complete machine learning lifecycle, covering data collection, annotation strategies, training, evaluation, deployment, monitoring, and post-launch iteration loops.
Optimize model performance under challenging real-world physical conditions, including occlusion, low lighting, lens distortion, camera movement, viewpoint variation, and domain shift across diverse store environments.
Guide model optimization for constrained edge hardware, carefully balancing accuracy against latency, memory, throughput, and operational reliability.
Develop reusable pipelines and internal tooling to minimize manual effort in data preparation, store configuration, camera calibration, validation, and rollout.
Requirements
At least 7 years of professional experience in machine learning, deep learning, or computer vision, backed by a proven track record of delivering production-level computer vision systems.
Prior experience leading a machine learning team, acting as a technical lead, or owning the direction and delivery of major machine learning products.
Deep technical knowledge in one or more core areas like object detection, multi-object tracking, person or vehicle re-identification, segmentation, or video understanding.
Solid foundation in classical computer vision and image processing, including feature extraction, geometric transformations, interpolation, and image warping.
Strong judgment for evaluating computer vision systems under real-world operational constraints and identifying customer-impacting failure modes.
Comprehensive experience managing the end-to-end machine learning product lifecycle from dataset development to production monitoring.
Proficiency in Python alongside PyTorch or TensorFlow, with a strong understanding of model evaluation, error analysis, dataset quality, and experiment design.
Ability to bridge ambiguous product requirements with measurable objectives, collaborate across functions, and stay technically hands-on while leading people.
Nice to Have
Specialized knowledge in camera geometry and calibration, including pinhole camera models and intrinsic and extrinsic parameters.
Edge AI and on-device inference expertise utilizing TensorRT, ONNX, OpenVINO, NVIDIA Jetson, DeepStream, quantization, pruning, or distillation.
MLOps background covering dataset and model versioning, experiment tracking, automated evaluation, model monitoring, and progressive rollouts.
Experience applying computer vision in uncontrolled physical environments such as autonomous driving, robotics, security, industrial inspection, or smart retail.
Familiarity with multimodal models, vision-language models, or large language model-based workflows in production.
Background in startup environments, fast-scaling product organizations, or working alongside international teams and enterprise customers.
Skills and Tools
Python
PyTorch
TensorFlow
LLM
Computer Vision
MLOps
About the Company
Berry AI creates AI-powered operations platforms tailored for quick-service restaurants, providing drive-thru analytics, loss prevention, and store management tooling deployed at thousands of locations across the United States. Computer vision serves as the core of its technology, executing models on in-store edge devices that analyze video streams of vehicles, people, queues, and operational events under real restaurant conditions.
How to Apply
To apply for this position, please visit the official company careers page of Berry AI to submit your application details.
