Backend Engineer (AI)

TL;DR

Backend Engineer (AI): Building and operating the inference and orchestration layer for a proactive smart assistant with an accent on low-latency APIs and high-throughput systems. Focus on designing inference pipelines and ensuring system reliability despite non-deterministic AI model behavior.

Location: Remote (China)

Company

hirify.global is developing a proactive smart assistant designed to bring intelligence to conversations, errands, and workflows for billions of users globally.

What you will do

• Build and operate production backend systems that serve AI-powered features.
• Design inference pipelines, orchestration layers, and service boundaries around models.
• Manage production operations, including monitoring, logging, alerting, and incident response.
• Optimize latency and throughput across inference, caching, batching, and streaming.
• Ensure APIs are stable and support seamless integration with frontend and ML systems.

Requirements

• Strong backend engineering fundamentals in production environments.
• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns including LLMs, embeddings, and multimodal models.
• Proficiency in debugging distributed systems under load.
• Technical stack: Python, NodeJs, Pytorch, SQL, NoSQL, Kubernetes, and Docker.
• Bias toward shipping and learning from production behavior.

Culture & Benefits

• High talent density environment with a hands-on, world-class team.
• Collaborative decision-making and rapid execution speed.
• Balance between maintaining high-quality standards and iterative learning.
• Opportunity to work on a product with global impact for billions of users.

Hiring process

• Technical evaluation of applications by team members.
• 3 to 4 interviews conducted via virtual meetings and/or onsite.
• Transparent and efficient process with prompt decision-making.