Lead Architect - Gen AI API Platform

About the Role

We are seeking a Lead Architect to spearhead the architecture, design, and development of our next-generation Gen AI API platform. This platform supports multiple modalities, including image, video, language, 3D, and audio. The ideal candidate will have extensive experience in architecting and building REST APIs, hosting AI/ML workflows on HPC clusters, setting up AWS infrastructure, and mentoring junior developers.

Responsibilities

• Serve as the technical lead to drive architecture, design, and development of AI/ML SaaS services.
• Set up inference on an HPC cluster for multiple modalities on a common Gen AI platform.
• Build robust application backends on AWS infrastructure that support highly available AI/ML services at high scale, efficiently utilizing GPU clusters.
• Define comprehensive API specifications and documentation.
• Deliver customer-facing services, including account management, identity, single-sign-on, subscription billing, and self-service support tools, integrating with existing internal systems where necessary.
• Collaborate with stakeholders such as the frontend team, product managers, and technical leadership to implement new features.
• Lead system architecture design and decisions, helping drive consensus.
• Manage large compute clusters for ML inference and development.
• Deliver and manage our developer and researcher productivity tools, including CI/CD pipelines for deploying new machine learning models, orchestration, continuous/progressive deployments, test environments, feature flags, and GitHub.
• Own the orchestration, deployments, middleware, and any other microservices required to meet the needs of our API customers.

Qualifications

• 10+ years of experience in building REST APIs and backend infrastructure on AWS.
• Experienced in designing and building AI/ML infrastructure and working with large GPU clusters, preferably in multiple modalities like image, video, audio, and language.
• Distributed system architecture design knowledge and experience with delivering high traffic and highly available SaaS type services.
• Well-versed in data structures, data modeling, and database management systems, billing and metering, as well as object and file storage systems.
• Experienced in mentoring other engineers and collaborating with multiple stakeholders.
• Experienced in root cause analysis and driving operational excellence initiatives of AI/ML services.
• Highly proficient in Python and Typescript.

Compensation

The salary range for this role is between $190,000 and $250,000. Total compensation also includes stock options and benefits.

Equal Employment Opportunity

We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability, or other legally protected statuses.