Full Time Computer Vision Jobs in Massachusetts (NOW HIRING)

Are you inspired by invention. Is problem solving through teamwork in your DNA. Do you like the idea of seeing how your work impacts the bigger picture.

Answer yes to any of these and you'll fit right in here at Amazon Robotics. We are a smart team of doers who work passionately to apply industry leading advances in robotics and software to solve real-world challenges that will transform our customers' experiences. We invent new improvements every day.

We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling, and fun.
The Scanless Technologies team at Amazon is eliminating manual barcode scanning across one of the world's largest fulfillment and delivery networks using computer vision, machine learning, and advanced sensor systems. Our technology, Amazon Robotics Identification (AR-ID), reads multiple barcodes in real time and powers innovations like Vision-Assisted Package Retrieval (VAPR) inside Amazon's electric delivery vans. Our platform spans sensors, edge inference, cloud training, and robust observability, and it's deployed across thousands of workcells shipping millions of packages daily.
We are looking for Software Engineers with a strong focus on real-world Robotics, Signal Processing and Computer vision, to bring new product ideas to life and reimagine how we delight our customers with the help of Machine Learning and computer-vision-based solutions

Familiarity with theoretical foundations is equally important as a builder mindset with strong coding and practical problem solving skills. At Amazon Robotics, candidates have an opportunity to drive projects from research concept to a working prototype and beyond. The candidate should have a strong desire to move quickly to solve Amazon's business problems via a structured approach.

Key job responsibilities
- Design, build, and maintain end-to-end solutions that automate data collection, processing, annotation, model training, validation, and deployment for computer vision models operating across thousands of edge devices in production.
- Collaborate with applied scientists and ML engineers to operationalize research models into production-ready pipelines, bridging the gap between offline experimentation and real-world deployment on constrained edge hardware.
- Partner with hardware and optics teams to validate sensor configurations, calibration accuracy, and image quality requirements that directly impact model performance, closing the feedback loop between field hardware and ML training.
- Participate in on-call rotations, triaging ML pipeline failures and model performance degradations in production, performing root cause analysis, and driving resolution to maintain fleet-wide model health.
- Implement automated test frameworks including unit, integration, stress, hardware-in-the-loop, and long-running reliability test suites that validate end-to-end system behavior across cloud and edge boundaries before every production deployment
- Mentor junior engineers through code reviews, design discussions, and technical guidance, raising the team's overall engineering quality and helping SDE-1s grow toward independent ownership of complex features.
A day in the life
A typical day for an ML SDE-2 on the Scanless Technologies team starts with experimenting on model architectures or tuning hyperparameters for a computer vision model that detects, classifies, or dimensions items across thousands of fulfillment workcells, then evaluating precision, recall, and impact against the latest field data. By mid-morning, the engineer might be prototyping a new feature extraction approach to improve barcode identification under challenging lighting conditions, running offline evaluation benchmarks on a freshly trained model variant, or writing inference optimization code to meet latency constraints on edge hardware. Afternoons often shift to collaborating with applied scientists on a novel model architecture for a new workcell type, working with hardware and optics engineers to understand how sensor placement and image quality affect model accuracy, or building robust training and evaluation pipelines that enable rapid experimentation across multiple model families

The day might close with a code review for a junior engineer, analyzing model error patterns from production telemetry data to identify the next high-impact training data strategy, or designing a scalable service that serves model predictions at the edge.
Amazon offers a full range of benefits that support you and eligible family members, including domestic partners. Benefits can vary by location, the number of regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include:
1

Medical, Dental, and Vision Coverage
2. Maternity and Parental Leave Options
3. Paid Time Off (PTO)
4.

401(k) Plan
If you are not sure that every qualification on the list above describes you exactly, we'd still love to hear from you. At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you're passionate about this role and want to make an impact on a global scale, please apply.

About the team
The Scanless Technologies team at Amazon is reimagining how items are identified, measured, and inspected across one of the world's largest fulfillment and delivery networks, all without manual barcode scanning. Our flagship technology, Amazon Robotics Identification (AR-ID), uses computer vision and machine learning to locate and read multiple barcodes in real time while being linked to variety of sensors, powering everything from fulfillment center workcells to Vision-Assisted Package Retrieval (VAPR) inside Amazon's electric delivery vans.
If you're excited about building full-stack systems that span sensors, edge computing, and machine learning-and shipping them to thousands of real-world deployments where they make a measurable difference every day-Scanless Tech is the place to do it.