Maitai manages the LLM stack for enterprise companies, enabling the fastest and most reliable inference. The future of enterprise AI revolves around mosaics of small, domain-specific models powering powerful, responsive agents, and Maitai is well positioned to capture the market. If you're looking at getting in early with a company redefining how large companies build with AI, then let's talk.

High-level

Help us reshape how enterprise companies build with LLMs. You'll collaborate with founders, 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. We’re at an inflection point: demand is exploding, new customers are pushing us to scale faster than ever, and we’re looking for 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. You’ll 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, you’ll 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
• You’ve built and shipped real systems end-to-end
• Hobbies? You mean side projects?
• You have strong opinions
• You’ll 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 – We’re 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. If you're comfortable just being told what to do, then this isn't the gig for you.
• 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 time—unlocking entirely new product possibilities. Top YC startups and public companies rely on us to manage their model stack.

Infra

As LLMs are core to our customers' products, resiliency and uptime are our top priorities. Since we act as a proxy, our uptime must exceed that of the providers themselves. We’re multi-cloud, multi-region, and built for seamless failover. Our infrastructure runs on Kubernetes, managed with Terraform, and deployed across AWS and GCP. We use GitHub Actions for CI/CD, with Datadog for monitoring, tracing, and performance insights.

Infra stack: Kubernetes, Terraform, AWS, GCP, GitHub Actions, PostgreSQL, Redis, Datadog.

Backend

Our backend is a set of microservices running Python with Quart for web services and Python-based fine-tuning jobs optimized for speed, cost, and accuracy. We use PostgreSQL for conventional data persistence and vector storage. Go is being introduced where performance gains are critical.

Tech stack: Python (Quart), Go (in transition), PostgreSQL.

Frontend

Tech stack: React (Typescript)