Software Development Engineer, Amazon Optics

Come build intelligent systems that secure the foundation of our cloud using computer vision and applied machine learning to automate real-time production decisions that protect every AWS location globally. The Amazon Optics team builds and manages services used by AWS employees to secure our physical sites. Our services allow customers to protect AWS locations and preserve the trust that all AWS users have in us. You will work with other software development engineers and Applied Scientists every day to build, deploy, and optimize machine learning models that automate real-time security decisions at scale. The models you build and operate will run across every AWS region, making automated determinations that directly impact the physical security posture of every AWS customer. You will partner directly with Applied Scientists to translate research into production-grade inference pipelines. You will own the full lifecycle of ML model deployment: from training infrastructure through real-time serving, monitoring, and iteration. You will build the systems that take a model from notebook to production, ensuring low-latency inference at scale with high reliability. Our team provides solutions where "can't be done" is not an answer. You will stretch yourself and grow. You will share your knowledge with others and help others achieve. You will be empowered to automate away operational inefficiencies for both the team and our customers. You will solve complex architecture problems with solutions that are extensible and scale, yet always look for ways to simplify. You will work with the team on multiple products deployed to every AWS region using AWS services in a fully IaC deployment environment where you own everything end to end: design, development, testing, deploying. You will join a team that values strong intuition but seeks metrics and data to validate assumptions. Key job responsibilities Build and deploy machine learning models that automate real-time physical security decisions across all AWS regions Partner with Applied Scientists to operationalize research models into production-grade inference pipelines Own the full ML model lifecycle: training infrastructure, real-time serving, monitoring, retraining, and iteration Design and implement low-latency, high-reliability distributed systems for model serving at scale Build computer vision pipelines that process video and image data for automated threat detection Develop and maintain Infrastructure as Code (IaC) for all ML and application infrastructure Monitor model performance in production, identify drift, and drive continuous improvement Contribute to system design and architecture decisions that balance innovation with operational excellence Participate actively in code reviews, providing meaningful feedback to peers and senior engineers Collaborate cross-functionally with security operations, hardware, and product teams to define requirements Drive operational excellence through automation, runbooks, and proactive risk mitigation Mentor team members and contribute to a culture of knowledge sharing and technical growth About the team Diverse Experiences Amazon Security values diverse experiences. Even if you do not meet all of the qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn’t followed a traditional path, or includes alternative experiences, don’t let it stop you from applying. Why Amazon Security? At Amazon, security is central to maintaining customer trust and delivering delightful customer experiences. Our organization is responsible for creating and maintaining a high bar for security across all of Amazon’s products and services. We offer talented security professionals the chance to accelerate their careers with opportunities to build experience in a wide variety of areas including cloud, devices, retail, entertainment, healthcare, operations, and physical stores. Inclusive Team