Note: The job is a remote job and is open to candidates in USA. Throttle helps companies reduce the cost of running large language models on their own infrastructure through semantic caching and inference optimization. The Founding Backend Engineer will design, build, and optimize backend services powering the semantic cache and inference pipeline, with responsibilities spanning high-performance APIs, distributed systems, observability, documentation, and early customer collaboration.
Responsibilities
- Design, build, and optimize core backend services that power the semantic cache and inference pipeline
- Work on high-performance APIs, distributed systems, and caching layers, ensuring low-latency, highly reliable integrations with popular LLM serving frameworks
- Write production-grade code, design system architecture, improve observability and performance, and collaborate closely with the founders on product and technical direction
- Help shape engineering best practices, contribute to technical documentation, and engage with early customers to understand requirements and iterate quickly
Skills
- Strong programming skills with experience in Back-End Web Development and Software Development for production systems
- Solid understanding of Object-Oriented Programming (OOP) principles and modern Programming practices
- Ability to collaborate with Front-End Development teams to design clean interfaces and robust APIs
- Background in building scalable infrastructure, distributed systems, or high-throughput services, ideally in LLM or ML-related environments
- Experience with performance optimization, profiling, and monitoring of backend services
- Comfort working in an early-stage startup environment, including ownership of projects from design through deployment
- Strong communication skills and ability to work closely with product, customers, and other engineers
- Bachelor's degree in Computer Science, Engineering, or equivalent practical experience is beneficial
Benefits
- Remote work
Company Overview