You’re an engineer who lives and breathes high-performance machine learning. You have a deep understanding of how to make AI models run faster and more efficiently, and you’re excited about pushing the boundaries of what’s possible with current hardware.

At Replicate, we’re building the fastest way to deploy machine learning models. Your role will be crucial in optimizing the performance of the diverse range of models we host, ensuring they run as efficiently as possible on our infrastructure.

We’re looking for the right person, not just someone who checks boxes, so you don’t need to satisfy all of these things. But, you might have some of these qualities:

• Strong applied engineering skills. You’ve deployed machine learning models in scaled-up production environments and know the challenges that come with it.
• Deep expertise in CUDA programming and GPU acceleration techniques. You can write custom kernels in your sleep.
• Proficiency in C++ and Python. You’re comfortable diving deep into low-level optimizations and high-level model architectures alike.
• Extensive experience with deep learning frameworks like Torch or JAX. You know their strengths, weaknesses, and how to squeeze every ounce of performance out of them.
• A solid grasp of machine learning algorithms, especially with a focus on diffusion models, large language models, or other generative AI techniques.
• Familiarity with model quantization techniques, distillation, model pruning, etc. You understand the tradeoffs and know when to apply which technique.
• You stay up-to-date with the latest developments in ML performance optimization. When a new technique drops, you’re already thinking about how to implement it.

You might be particularly good for this job if:

• You’ve written custom CUDA kernels to significantly improve model latency and can share war stories about the process.
• You can discuss the tradeoffs between fp8 and int8 quantization in depth, and have applied either (or both) to whatever hot new model dropped last week.
• You get excited about diving into academic papers on ML optimization techniques and turning them into practical, production-ready code.

Email us jobs@replicate.com

You’re a generalist data and analytics expert who thrives on developing data infrastructure at scale. You act like an owner and feel a desire to lead; you’ve likely been a data engineer at traditional companies but you’re ready to amplify your impact as the first data hire at a leading AI startup.

Replicate is building the fastest way to deploy machine learning models. We offer access to all types of open source models across modalities and levels of customization. The business is complex and we need a solid data foundation to guide decisions and hold ourselves accountable. You’ll be responsible for owning this foundation across the company.

We’re looking for the right person, not just someone who checks boxes, so you don’t need to satisfy all of these things. But you probably have some of these qualities:

• Think like a software engineer: You put things in GitHub, use continuous integration, give things good names, make it consistent with how we do things in the product. We want to create data systems that integrate with the rest of our systems, not their own silo with a different culture.
• Experience building 0→1: You’ve set up data stacks and pipelines from scratch in the past.
• Expert with SQL and other common analytics tools: You know your way around BI tools like Metabase and can leverage them to deliver actionable insights.
• Agility and efficiency: You can move fast and prioritize effectively, delivering 80/20 solutions that address core needs.
• Experience with usage-based businesses: You understand the nuances of analyzing usage-based businesses from the ground up.
• Collaboration and partnership: You can work collaboratively with Finance, Product, Infrastructure, and Growth teams to create and maintain dashboards that measure key business metrics. You’re a solid communicator and can help teams pull together a story; you go beyond reporting metrics, diving deeper to understand what’s driving the numbers.

This role is based in our San Francisco office.

Email us jobs@replicate.com

You’re an engineer who dreams in cycles and optimizations. You have a deep passion for squeezing every ounce of performance out of complex systems, whether that’s rendering the latest AAA game title or optimizing large-scale distributed systems.

At Replicate, we’re building the fastest way to deploy machine learning models. We’re looking for someone who can bring their performance optimization expertise to the cutting edge of AI infrastructure.

We’re looking for the right person, not just someone who checks boxes, so you don’t need to satisfy all of these things. But, you might have some of these qualities:

• Mastery of C++ and a deep understanding of systems programming. You know your way around pointers, memory management, and low-level optimizations.
• Experience with high-performance computing environments. Whether it’s game engines, financial systems, or scientific simulations, you’ve worked on projects where every microsecond counts.
• Comfort with parallel programming models. You’ve wrestled with multi-threading, SIMD instructions, or GPU programming (like CUDA or similar).
• A track record of optimizing large-scale production deployments. You understand the challenges of performance at scale and how to address them.
• An insatiable curiosity about new technologies and techniques. You’re always looking for the next tool or approach that could give your code that extra boost.
• Excellent problem-solving skills. You enjoy diving into complex performance issues and emerging with elegant, efficient solutions.

You might be particularly good for this job if:

• You’ve optimized rendering pipelines for video games or real-time graphics applications.
• You’ve worked on high-frequency trading systems where nanoseconds make a difference.
• You’ve contributed to open-source projects focused on performance-critical libraries or tools.
• You get excited about diving into unfamiliar codebases and finding unexpected optimizations.
• You have experience profiling and optimizing applications across different hardware architectures.

While prior experience with AI or machine learning isn’t required, you should be excited about applying your performance optimization skills to this domain. We believe your expertise in cycles, memory management, and systems-level thinking will translate well to the challenges of optimizing AI model inference and training.

Email us jobs@replicate.com

You’ll be responsible for working with hiring managers and our teams to understand needs, develop recruiting strategies, and ensure a candidate experience that feels like Replicate. The goal is to get the right people into Replicate, whatever it takes.

You are a technical recruiter with a deep understanding of the startup space (bonus points for experience in gen ai), excellent communication skills and a proven track record in sourcing, engaging, and hiring candidates for highly technical roles.

We’re looking for the right person, not just someone who checks boxes, so you don’t need to satisfy all of these things. But, you might have some of these qualities:

• Outstanding communication skills. You’ll be the first person interacting with most candidates.
• Comfort running a full desk. You like to be the one who handles sourcing to closing and building those trusting relationships with your candidates.
• Deep experience hiring software engineers. You are a tough critic and take ownership to ensure on the best candidates get through our screens.
• Scrappy, startup energy. You are joining a small team and will help continue to build the foundation of recruiting at Replicate.

This role is based in our San Francisco Office.

Email us jobs@replicate.com