ML Ops Engineer (AWS / Terraform)
Location: Remote
Engagement: Permanent or Contract
About the Role
We’re looking for an experienced ML Ops Engineer to help scale the deployment and management of multiple AI models across AWS. You’ll be working with a growing team that has built a suite of image-based machine learning models - including classification, recognition, and prediction systems - and now needs to operationalise these models efficiently and securely in production environments.
This role sits at the heart of our platform and infrastructure strategy. You’ll be responsible for identifying the best approaches to model deployment, building scalable infrastructure using Terraform, and ensuring that the entire ML lifecycle - from experimentation to production - runs smoothly and cost-effectively.
Key Responsibilities
* Design and implement scalable, automated infrastructure for deploying ML models in AWS, using Terraform as the primary provisioning tool.
* Manage and optimise existing AWS environments (SageMaker, ECS/EKS, Lambda, Batch, and GPU-backed instances).
* Build and maintain CI/CD pipelines for ML model delivery and monitoring.
* Ensure the infrastructure can support both real-time inference and batch processing workloads.
* Collaborate closely with Data Scientists and Engineers to productionise models efficiently.
* Monitor system performance and cost, identifying opportunities for optimisation and automation.
* Maintain infrastructure security, reliability, and compliance with best practices.
Essential Skills & Experience
* Extensive hands-on experience with Terraform, including provisioning and managing complex AWS infrastructure.
* Strong knowledge of AWS services relevant to ML Ops:
* SageMaker for model training and deployment
* ECS/EKS or Elastic Beanstalk for containerised workloads
* Lambda and Batch for inference pipelines
* S3, CloudWatch, IAM, Glue, and related orchestration tools
* Proven experience deploying GPU-accelerated models in production.
* Solid understanding of ML model lifecycle management, including versioning, packaging, and scaling.
* Competence in Python and experience with frameworks such as FastAPI or Flask for serving models.
* Strong understanding of CI/CD, infrastructure as code, and DevOps principles.
Desirable Skills
* AWS Certified (Solutions Architect, DevOps Engineer, or Machine Learning Specialty).
* Terraform Certification.
* Familiarity with Kubernetes, Docker, and MLflow.
* Experience in cost optimisation and performance tuning within AWS.
What We’re Looking For
This is a critical role - the infrastructure you build underpins the company’s ability to deliver and scale its AI products. We’re looking for someone who combines strong technical expertise with sound judgment and reliability. You should be confident working autonomously in production environments where infrastructure changes can have major impact.