Software Engineer - ML Platform

Replicate is revolutionizing AI accessibility by building the premier platform for creating, deploying, and running machine learning models. As an Infrastructure Engineer on the Platform team, you'll be at the forefront of democratizing AI technology.

The role involves managing the complete lifecycle of ML models, from packaging to deployment, serving, scaling, and monitoring. You'll be working with a system that handles thousands of models and millions of daily predictions. The platform team is responsible for critical infrastructure that powers AI accessibility for developers worldwide.

Key Technical Aspects:

• Working with Python, Go, Node.js, Kubernetes, and Terraform
• Managing complex distributed systems and GPU resources
• Optimizing model inference and deployment processes
• Handling multi-regional traffic and failover capabilities
• Working with databases like Redis, Google BigQuery, and PostgreSQL

Company Culture:

• Engineering-led organization with a focus on technical excellence
• Strong emphasis on in-person collaboration at their Mission, San Francisco office
• Team composed of experienced professionals from companies like Docker, Dropbox, GitHub, Heroku, NVIDIA
• Open-source focused with a commitment to building in public
• Strong emphasis on API design and infrastructure reliability

The role offers an opportunity to:

• Shape the future of AI accessibility
• Work with cutting-edge ML/AI technologies
• Build scalable systems that impact thousands of developers
• Join a team of experienced engineers from top tech companies
• Contribute to making AI technology more accessible and safer

This position is perfect for someone who combines strong infrastructure engineering skills with a passion for democratizing AI technology. You'll be working in a fast-paced environment where your decisions directly impact the platform's success and the broader AI developer community.