AI Systems Engineer — Scalable, Production-Ready ML

Univers; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Univers Global AI Lab is seeking an AI Engineer to design and build scalable AI systems bridging research and real-world deployment across enterprise verticals. You will partner with Applied AI and AIoT Scientists to transition prototypes into production-ready pipelines, optimize inference performance, and ensure low-latency, high-throughput systems across cloud, hybrid, and edge environments.

You'll work across 0-1 and scaling environments, shaping architectures, model lifecycles, and

Qualifications

• Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, or a related field (or equivalent industry experience)
• Strong proficiency in Python and experience with PyTorch for model development and experimentation
• Experience building and optimizing training and inference pipelines for machine learning systems
• Familiarity with MLOps and model lifecycle management practices
• Experience working with containerization and orchestration technologies such as Docker and Kubernetes
• Experience optimizing foundation model inference performance and understanding runtime efficiency trade-offs
• Strong understanding of system-level considerations, including latency, throughput, scalability, and reliability
• Ability to collaborate effectively across research, product, and engineering teams
• Excellent communication skills

Responsibilities

• Partner with Applied AI and AIoT Scientists to transition prototypes into scalable, production-aligned architectures
• Design and implement end-to-end training, evaluation, and inference pipelines
• Develop and refine agentic frameworks that orchestrate model reasoning, tool integration, and workflow execution
• Optimize foundation model inference performance using techniques such as KV caching, batching strategies, quantization, and optimized runtimes (e.g., vLLM or similar frameworks)
• Define and architect systems that meet real-world constraints, including latency, throughput, scalability, and runtime efficiency
• Establish best practices for AI infrastructure, including containerization (Docker), orchestration (Kubernetes), and model lifecycle management
• Collaborate with product and engineering teams to integrate validated AI capabilities into scalable platform components
• Engage with technical stakeholders to ensure system performance and deployment readiness

Skills

Python

PyTorch

MLOps

Docker

Kubernetes

Education

Bachelor's/Master's/Ph.D. in Computer Science or related field

Tools

Docker

Kubernetes

vLLM

Job description

Univers Global AI Lab is seeking an AI Engineer to design and build scalable AI systems bridging research and real-world deployment across enterprise verticals. You will partner with Applied AI and AIoT Scientists to transition prototypes into production-ready pipelines, optimize inference performance, and ensure low-latency, high-throughput systems across cloud, hybrid, and edge environments.

You'll work across 0-1 and scaling environments, shaping architectures, model lifecycles, and