Ai Deployment & Platform Engineer

 

Description:

We are hiring an AI Deployment & Platform Engineer to build and operate the infrastructure layer powering our AI systems in production.

You will work directly with the AI systems engineering team to deploy AI systems into live environments, manage runtime infrastructure, scale orchestration systems, optimise inference performance, and build the deployment pipelines and observability that keep everything running.

This is a deeply hands-on engineering role for someone who enjoys building production infrastructure, solving operational problems, and making AI systems reliable at scale.

What You Will Build

Deployment Infrastructure

• Deploy and manage AI systems primarily across AWS and Azure, with Alibaba Cloud for China-based deployments and GCP as workloads require

• Containerise and orchestrate AI workloads at scale

• Build CI/CD pipelines for AI systems and model deployments

• Manage inference infrastructure and deployment automation

• Design scalable runtime environments for multi-agent systems

 

Reliability and Scaling

• Monitor system performance, latency, throughput, and uptime

• Build observability, logging, and alerting systems

• Manage autoscaling and infrastructure optimisation

• Debug production failures and runtime bottlenecks

 

Infrastructure Operations

• Monitor model drift, data drift, and runtime quality degradation

• Implement rollback, failover, and deployment safety systems

• Manage GPU infrastructure and workload scheduling

• Optimise model serving costs and cloud spend

You will support deployment and operations for organisational intelligence platforms, large-scale prediction systems, multi-agent workflows, multimodal AI systems, and future AI-native SaaS products.

Who You Are

You have 3+ years of experience operating production infrastructure under real-world conditions. You are highly hands-on and comfortable owning systems directly. You understand that AI systems are operational systems, and that reliability, latency, observability, and cost control matter as much as model quality.

You write production code regularly. Python is expected.

Strong experience across the following is highly valuable:

• containerisation and orchestration

• major cloud platforms (AWS, Azure)

• infrastructure-as-code

• backend API frameworks

• caching layers and in-memory data stores

• relational and vector databases

• workflow orchestration

• CI/CD pipelines

• GPU infrastructure

• monitoring and observability stacks

 

A strong plus:

• inference optimisation

• model serving runtimes

• async and streaming systems

• MLOps tooling

• multi-agent systems

• Alibaba Cloud or other China cloud providers