AI Architect: Scalable ML Pipelines & Inference

DADACONSULTANTS PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Dada Consultants Pte Ltd in Singapore seeks an experienced ML Platform Engineer to transform AI prototypes into scalable, production-ready architectures and platform components.

You will build end-to-end model training, evaluation, inference, and deployment pipelines, and establish MLOps practices using Docker, Kubernetes, and lifecycle management.

Collaborate with research, product, and engineering teams to deliver robust, production-grade AI capabilities across the business.

Qualifications

• Strong software/AI engineering background with relevant industry experience.
• Proficiency in Python and PyTorch.
• Experience building and optimizing ML training and inference pipelines.
• Familiarity with MLOps, model serving, and lifecycle management.
• Hands-on experience with Docker, Kubernetes, and scalable infrastructure.
• Understanding of LLM/foundation model inference optimization and runtime performance.
• Strong system design skills covering scalability, latency, throughput, and reliability.
• Strong problem-solving, collaboration, and communication skills.

Responsibilities

• Transform AI prototypes into scalable, production-ready architectures and platform components.
• Build end-to-end model training, evaluation, inference, and deployment pipelines.
• Develop agentic frameworks for model reasoning, tool integration, and workflow orchestration.
• Optimize model inference using techniques such as KV caching, batching, quantization, and optimized runtimes such as vLLM.
• Design systems for latency, throughput, scalability, reliability, and runtime efficiency.
• Establish AI infrastructure and MLOps practices using Docker, Kubernetes, and model lifecycle management.
• Collaborate with research, product, and engineering teams to deliver production-ready AI capabilities.

Skills

Python

PyTorch

Docker

Kubernetes

MLOps

LLM inference optimization

System design

Collaboration & communication

Tools

Docker

Kubernetes

Job description

Dada Consultants Pte Ltd in Singapore seeks an experienced ML Platform Engineer to transform AI prototypes into scalable, production-ready architectures and platform components.

You will build end-to-end model training, evaluation, inference, and deployment pipelines, and establish MLOps practices using Docker, Kubernetes, and lifecycle management.

Collaborate with research, product, and engineering teams to deliver robust, production-grade AI capabilities across the business.