AI Backend Engineer - Production-Ready Inference Systems

GMP RECRUITMENT SERVICES (S) PTE LTD; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

GMP Technologies (S) Pte Ltd is seeking a backend engineer to optimize production systems powering AI features. You will tune latency across inference, caching, batching and streaming, and own production operations including monitoring and incident response.

You will develop backend services for AI in production, design inference pipelines and model boundaries, and work with Kubernetes, Python, Docker and ML stacks to enable high-throughput workloads.

Qualifications

• Troubleshooting distributed systems under heavy load.
• Familiarity with AI inference patterns such as LLMs, embeddings and multimodal models.
• Focus on shipping and learning from how systems behave in production.
• Solid backend engineering fundamentals in production environments.
• Experience operating high-throughput, low-latency services.

Responsibilities

• Tune latency and throughput across inference, caching, batching and streaming.
• Take ownership of production operations, including monitoring, logging, alerting and incident response.
• Develop and run backend systems that power AI features in production.
• Design inference pipelines, orchestration layers and service boundaries around models.

Skills

Distributed systems

Low-latency systems

Backend engineering

Production monitoring

Incident response

Tools

Kubernetes

Python

Docker

Node.js

PyTorch

SQL/NoSQL

Job description

GMP Technologies (S) Pte Ltd is seeking a backend engineer to optimize production systems powering AI features. You will tune latency across inference, caching, batching and streaming, and own production operations including monitoring and incident response.

You will develop backend services for AI in production, design inference pipelines and model boundaries, and work with Kubernetes, Python, Docker and ML stacks to enable high-throughput workloads.