Software Engineer – AI Platform / LLM Gateway
About the role
We are building an AI gateway product, *************, to help enterprise customers deploy AI workloads securely and efficiently. The product focuses on LLM API aggregation, audit trails, private/VPC deployment, cost control, reliability, and enterprise readiness. The role is a hands-on software engineering position in a small senior engineering team. The team currently uses mainly Python, TypeScript and React, with possible Go adoption for selected scaling needs.
What you’ll do
- Build backend and platform features for the AI gateway / LLM routing product.
- Work on API services, access control, audit logs, deployment tooling and observability.
- Support private cloud, VPC and potential on-prem deployment scenarios.
- Improve platform scalability, reliability, load testing and production readiness.
- Own technical features end-to-end in a lean, senior, hands-on engineering team.
What we’re looking for
- Strong backend/platform engineering experience.
- Hands-on experience with Python and/or TypeScript; React is a plus.
- Experience with cloud infrastructure, APIs, distributed systems, Kubernetes, Helm, Terraform or similar tools.
- Good understanding of system reliability, scalability, testing and performance trade-offs.
- Interest in AI infrastructure, LLM applications, API gateways or developer platforms.
- Ability to work independently and collaborate with a distributed team in GMT+8 time zones.
Bonus points
- Experience with LLM APIs, AI gateways, agents, RAG, model routing or AI infrastructure.
- Experience supporting enterprise customers, private deployment or compliance-related technical requirements.