Founding Engineer

Responsibilities

• Design, build, and own core backend infrastructure powering a high-throughput, production-grade AI gateway serving billions of tokens per day.
• Architect and evolve a pragmatic microservices system — including a core LLM gateway in Go and auxiliary ML/AI services in Python.
• Make critical decisions around distributed systems design, database selection, caching strategies, and API platform architecture.
• Profile and optimize performance for high-traffic, latency-sensitive systems (sub-20ms SLAs).
• Work hands-on with Kubernetes to deploy, manage, and scale services reliably.
• Redefine and evolve the tech stack as the product and team grow — you will be a key voice in those decisions.
• Collaborate directly with founders to translate product vision into robust, scalable engineering solutions.

• 5+ years of experience building backend services using a compiled language — Go (Golang) strongly preferred.
• Strong experience in distributed systems design and scalability.
• Hands‑on Kubernetes expertise in production environments.
• Deep knowledge of SQL/No
  
  SQL databases and caching layers — and the judgment to choose the right tool for the job.
• Experience building or designing high-quality API platforms.
• Experience with performance profiling and optimization for high-traffic systems.
• Prior experience at an early-stage startup or on greenfield/founding engineering projects.
• Strong understanding of concurrency patterns and how to apply them correctly.
• The ability to balance pragmatism with quality — you know that "minimal" is not the same as "broken".
• A self‑starter mindset: you've taught yourself new technologies before and are eager to do it again.

Demonstrates expertise in designing and building scalable backend infrastructure, with a strong focus on distributed systems, performance optimization, and microservices architecture. Proficient in leveraging Kubernetes for deployment and management of high-throughput AI services.