Design and implement public REST APIs, including data storage and ML backend services, and deliver highly available and scalable services that efficiently use a GPU cluster hosting the services.
Write clean and extensible Python and TypeScript code.
Deliver efficient design and implementation of the backend databases hosted on AWS to share user preferences, past user input, and generated content history optimized for low-latency responses.
Design and implement high-scale and low-latency REST APIs
Work closely with product management, design, research, and engineering teams to deliver high-quality and user-friendly products
Identify performance bottlenecks in APIs and deliver optimized solutions to address them.
Participate in incident management and root cause analysis to improve system reliability.
Implement and improve service telemetry and event tracking for the product.
Implement best practices to ensure that the applications can be efficiently tested and debugged to ensure they work as expected across multiple devices and browsers
Implement security measures to protect user data and prevent unauthorized access or data breaches.
Requirements & Skills:
7+ years in building REST APIs for AI/ML-based services in a high-scale environment.
Experienced in building robust backend services on AWS infrastructure, including databases to serve AI/ML services.
Define comprehensive API specifications and documentation.
Efficient AWS cloud database design and implementation for customer metadata and usage preferences.
Deliver customer-facing services, including account management, identity, billing, and metering, and self-service support tools, integrating with existing internal systems where necessary.
Excellent problem-solving skills and attention to detail
Highly Proficient in Python, TypeScript
Able to write comprehensive technical documentation
Proven ability to work in both rapid prototyping mode and to ship/maintain large-scale products.
