Maitai
High-level
Help us reshape how enterprise companies build with LLMs. You'll collaborate with founders, other engineers, and partners to create the management layer for enterprise AI stacks. Expect to tackle the hardest challenges surrounding LLMs in production while working at the cutting edge of opensource models and accelerated compute. Were at an inflection point: demand is exploding, new customers are pushing us to scale faster than ever, and were looking for ambitious engineers to help us meet it head-on. Low-level
We move fast and solve hard problems at every level of the stack. You'll be working on high-performance distributed systems that power our LLM proxy and fine-tuning infrastructure, ensuring models run reliably and efficiently. Our backend is built with Python (Quart) and Go, running on Kubernetes across AWS and GCP, with Terraform handling infrastructure as code. You'll optimize real-time LLM autocorrections, request routing, and backend latency, ensuring responses are fast and accurate. Youll also have the chance to improve our fine-tuning pipeline, balancing speed, cost, and accuracy to make training models as efficient as possible. On the frontend side, youll contribute to our Portal (React/TypeScript), where customers configure guardrails, fine-tune models, and test their stack. If you love working across the stack, making systems faster and more reliable, and solving real production AI challenges, you'll thrive here. Who You Are
Cursor/Windsurf is your best friend Youve built and shipped real systems end-to-end You contribute to your side projects in your free time You have strong opinions Youll call it a day after you shave off that last 5ms Why Join Us?
Big challenges Solving LLM reliability and continuous passive improvement at scale. High impact Define architecture, influence product, and shape company direction. Elite team Work with top engineers in a fast-moving environment. Equity upside Early team, meaningful ownership. No Red Tape Were still early, which means less process, more shipping, and absolutely zero Jira epics (for now). More You Need To Know
In-person downtown Redwood City. We'll hook you up with a Caltrain or parking pass, lunch, and Starbucks/Philz. Engineers make product decisions. Get ready to work with customers and push your own spec. We'll let you bite off as much as you can chew, and you'll get more and more opportunity if you prove you can handle it. About Us
Maitai ensures LLMs never fail by optimizing reliability, speed, and resilience. We act as an intelligent proxy, applying real-time autocorrections, rerouting requests, and fine-tuning models to maximize performance. We're growing fast, well-capitalized, and seizing a massive opportunity to redefine how enterprise companies build with AI. Our technology enables businesses to create AI models that are 10x faster and more accurate than closed-source alternatives, while also providing more reliable inference through online guardrails that catch and fix model failures in real timeunlocking entirely new product possibilities. Top YC startups and public companies rely on us to manage their model stack. #J-18808-Ljbffr
Help us reshape how enterprise companies build with LLMs. You'll collaborate with founders, other engineers, and partners to create the management layer for enterprise AI stacks. Expect to tackle the hardest challenges surrounding LLMs in production while working at the cutting edge of opensource models and accelerated compute. Were at an inflection point: demand is exploding, new customers are pushing us to scale faster than ever, and were looking for ambitious engineers to help us meet it head-on. Low-level
We move fast and solve hard problems at every level of the stack. You'll be working on high-performance distributed systems that power our LLM proxy and fine-tuning infrastructure, ensuring models run reliably and efficiently. Our backend is built with Python (Quart) and Go, running on Kubernetes across AWS and GCP, with Terraform handling infrastructure as code. You'll optimize real-time LLM autocorrections, request routing, and backend latency, ensuring responses are fast and accurate. Youll also have the chance to improve our fine-tuning pipeline, balancing speed, cost, and accuracy to make training models as efficient as possible. On the frontend side, youll contribute to our Portal (React/TypeScript), where customers configure guardrails, fine-tune models, and test their stack. If you love working across the stack, making systems faster and more reliable, and solving real production AI challenges, you'll thrive here. Who You Are
Cursor/Windsurf is your best friend Youve built and shipped real systems end-to-end You contribute to your side projects in your free time You have strong opinions Youll call it a day after you shave off that last 5ms Why Join Us?
Big challenges Solving LLM reliability and continuous passive improvement at scale. High impact Define architecture, influence product, and shape company direction. Elite team Work with top engineers in a fast-moving environment. Equity upside Early team, meaningful ownership. No Red Tape Were still early, which means less process, more shipping, and absolutely zero Jira epics (for now). More You Need To Know
In-person downtown Redwood City. We'll hook you up with a Caltrain or parking pass, lunch, and Starbucks/Philz. Engineers make product decisions. Get ready to work with customers and push your own spec. We'll let you bite off as much as you can chew, and you'll get more and more opportunity if you prove you can handle it. About Us
Maitai ensures LLMs never fail by optimizing reliability, speed, and resilience. We act as an intelligent proxy, applying real-time autocorrections, rerouting requests, and fine-tuning models to maximize performance. We're growing fast, well-capitalized, and seizing a massive opportunity to redefine how enterprise companies build with AI. Our technology enables businesses to create AI models that are 10x faster and more accurate than closed-source alternatives, while also providing more reliable inference through online guardrails that catch and fix model failures in real timeunlocking entirely new product possibilities. Top YC startups and public companies rely on us to manage their model stack. #J-18808-Ljbffr