Replicate is revolutionizing the AI landscape by democratizing access to machine learning capabilities for all software developers. As a Staff Software Engineer on the Platform team, you'll be at the forefront of making generative AI accessible to everyone.
The role involves working with the Platform team that manages the complete lifecycle of ML models - from packaging and deployment to serving, scaling, and monitoring. You'll be building infrastructure that supports thousands of models and handles millions of daily predictions. This position offers a unique opportunity to create innovative solutions where your decisions have direct impact.
The ideal candidate brings extensive experience in platform engineering, with a strong background in building scalable systems and working with technologies like Python, Go, Node.js, Kubernetes, and various databases. You'll be responsible for designing and implementing systems that maximize GPU utilization, handle complex workload distribution, and optimize model inference performance.
Working from Replicate's office in San Francisco's Mission district (minimum 3 days per week), you'll collaborate with talented engineers to solve challenging problems in AI infrastructure. The role offers competitive compensation ($230K-$280K) and the opportunity to work on cutting-edge AI technology.
What makes this role exciting is the chance to work at the intersection of infrastructure and AI, building systems that enable developers worldwide to harness the power of machine learning. You'll be dealing with unique challenges in resource optimization, system reliability, and performance tuning, all while making AI more accessible to the broader developer community.
The position requires strong technical expertise combined with excellent communication skills, as you'll be working closely with various teams to understand needs and translate complex technical concepts into actionable solutions. While direct ML experience isn't required, familiarity with ML platforms and production AI systems would be valuable.