Backend Engineer, AI
Summary
Builds and maintains backend systems that power an AI assistant, integrating large language models and orchestrating AI workflows for production use.
About Us
More than 5 billion people use everyday applications like email, notes, and task managers. Most of these apps are not built with AI. We are creating an AI assistant that helps users with conversations, daily tasks, planning, and work. It is designed to be simple to use and needs very little user input.
Our product is made to support long tasks, remember important information, and help users complete real work. It can solve problems in several steps, connect with external tools, and provide reliable results even when AI responses are not always predictable. Our goal is to help people finish daily tasks much faster while making the experience simple and enjoyable.
Role
As a Backend Engineer, AI, you will build and maintain the backend systems that support all AI features in our product. Your work connects AI models with users, so speed, reliability, accuracy, and cost are very important.
You will develop and manage production services that turn AI models into stable and efficient APIs used by mobile and desktop applications.
Main Responsibilities
Build and maintain backend services that deliver AI features in production.
Design inference pipelines, orchestration systems, and backend services around AI models.
Monitor production systems using logging, alerting, and incident management tools.
Improve system performance by reducing latency and increasing throughput with caching, batching, and streaming techniques.
Work with other engineering teams to build reliable and scalable AI services.
Requirements
Strong experience building backend systems for production environments.
Experience creating high-performance services with low latency and high throughput.
Knowledge of AI inference, including large language models, embeddings, or multimodal systems.
Ability to debug distributed systems under heavy workloads.
Interest in delivering solutions quickly and improving them based on production results.
Expected Results
Backend systems run reliably and support AI workloads at scale.
APIs are stable, easy to use, and integrate well with frontend and machine learning systems.
Production issues are detected, investigated, and solved quickly to reduce user impact.
Continuous improvements increase system speed, reliability, and overall performance.
Technologies
Python
Node.js
PyTorch
OpenAI, Anthropic, and open-source large language models
SQL and NoSQL databases
Kubernetes
Docker
How We Work
We believe the best products are built by small teams with excellent skills. We work closely together, make decisions as a team, and move quickly while maintaining high quality. We expect everyone to stay organized, make good decisions, and work independently.
Our goal is to create an AI product that gives real value to users.
Interview Process
If your experience matches our needs, we will invite you to 3 or 4 interviews.
Our technical team reviews every application. Interviews are held online or in person.
We keep the hiring process clear and efficient. If you show the skills and mindset we are looking for, we will invite you to join our team. We are looking for people who want to help build AI products that make a real difference for billions of users.