Remote AI Backend Engineer: Inference & Scale

JOINTHIRE SINGAPORE PTE. LTD.; Petaling Jaya; On-site; MYR 180,000 - 280,000; Full time

Benefits offered by this job

Remote work

WFH

Job summary

JOINTHIRE SINGAPORE PTE. LTD. is seeking an experienced AI backend engineer to own the inference and orchestration layer powering our AI interactions.

You will build and operate production systems that turn model capability into fast, stable APIs used across mobile and desktop clients, and design inference pipelines, orchestration layers, and model boundaries. Responsibilities include monitoring, logging, and incident response; optimizing latency and throughput; ensuring stable APIs for frontend

Qualifications

• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns (LLMs, embeddings, multimodal).
• Bias toward shipping and learning from production behavior.

Responsibilities

• Own the inference and orchestration layer powering AI interactions.
• Build and operate production systems exposing fast, stable APIs across clients.
• Design inference pipelines, orchestration layers, and model boundaries.
• Own production concerns: monitoring, logging, alerting, and incident response.
• Optimize latency and throughput across inference, caching, batching, and streaming.
• Ensure APIs are stable and integrate with frontend and ML systems.
• Ensure production incidents are quickly detected, diagnosed, and resolved.

Skills

High-throughput

Low-latency

AI inference patterns

Tools

Python

NodeJs

Pytorch

OpenAI/Anthropic/LLMs

SQL

NoSQL

Kubernetes

Docker

Job description

JOINTHIRE SINGAPORE PTE. LTD. is seeking an experienced AI backend engineer to own the inference and orchestration layer powering our AI interactions.

You will build and operate production systems that turn model capability into fast, stable APIs used across mobile and desktop clients, and design inference pipelines, orchestration layers, and model boundaries. Responsibilities include monitoring, logging, and incident response; optimizing latency and throughput; ensuring stable APIs for frontend