Remote Senior Backend Engineer - LLM Inference & APIs

HellaGoodAudio; United States; A distancia; USD 120.000 - 170.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health insurance

24 days annual leave + public holidays

Remote-friendly

Descripción de la vacante

Dizzaract is seeking a Senior Backend Engineer to own the architecture of our LLM inference platform. The role focuses on building reliable Go and TypeScript services with strong data models, streaming APIs, and scalable backend systems.

You will design OpenAI-compatible interfaces, manage token streaming, and ensure performance through caching, routing, and load balancing. A hands-on leader in a fast-paced, collaborative environment.

Formación

• 5+ years of professional backend engineering experience.
• Proficient in Go and TypeScript/JavaScript; Python a plus.
• Experience building and operating distributed systems with fault tolerance and scalability.
• Strong PostgreSQL knowledge: schema design, indexing, and transactions.
• Experience with streaming APIs (SSE/WebSockets) and LLM inference workflows.

Responsabilidades

• Design, build, and maintain backend services in Go and TypeScript/JS, plus Python where needed.
• Scale distributed systems to handle increasing traffic and complexity.
• Design OpenAI-compatible APIs for chat, streaming, and tool calls.
• Implement load balancing, backpressure, and admission control for variable-cost LLM workloads.
• Write automated tests and mentor engineers through code reviews.

Conocimientos

Go

TypeScript/JavaScript

Python

Distributed systems

LLM inference

Educación

Bachelor's degree in CS or related

Herramientas

PostgreSQL

Redis

Auth0/JWT

S3-compatible storage

Descripción del empleo

Dizzaract is seeking a Senior Backend Engineer to own the architecture of our LLM inference platform. The role focuses on building reliable Go and TypeScript services with strong data models, streaming APIs, and scalable backend systems.

You will design OpenAI-compatible interfaces, manage token streaming, and ensure performance through caching, routing, and load balancing. A hands-on leader in a fast-paced, collaborative environment.