Senior Backend Engineer - ML Platform

Responsibilities:

• Design, build, and enhance ML platform infrastructure to support the complete machine learning lifecycle, from model training to production deployment.
• Develop scalable model serving and inference systems with a focus on performance, latency, reliability, and cost optimisation.
• Build and maintain ML asset management solutions, including model versioning, experiment tracking, and governance.
• Design distributed inference pipelines that efficiently leverage hardware acceleration and cloud-native services.
• Build cloud-native, serverless solutions on AWS to support large-scale ML workloads.
• Collaborate with Machine Learning Engineers, Platform Engineers, DevOps, and QA teams to improve developer productivity and platform reliability.
• Evaluate and adopt new tools, frameworks, and technologies that improve the ML platform ecosystem.
• Contribute to the architecture and technical direction of distributed ML infrastructure.

Requirements:

• 4+ years of software engineering experience with strong Python development skills.
• Hands-on experience building or supporting production ML infrastructure or MLOps platforms.
• Experience with ML lifecycle management tools such as MLflow, Weights & Biases, or similar.
• Strong understanding of ML frameworks, preferably PyTorch.
• Experience deploying and optimising ML models using technologies such as ONNX, TensorRT, or AWS Neuron.
• Experience building cloud-native applications on AWS, including serverless services such as Lambda, SQS, SNS, and related services.
• Experience with Docker and containerised application deployment.
• Strong understanding of REST APIs and distributed system design.
• Good understanding of software engineering best practices, including code quality, testing, and security.
• Strong problem-solving, communication, and collaboration skills.

Nice to Have:

• Experience with model optimisation techniques such as quantisation, model compilation, or inference benchmarking.
• Experience improving inference performance for large-scale ML systems.
• Exposure to Kubernetes or container orchestration platforms.
• Experience working in regulated industries such as Healthcare, FinTech, or Identity Verification.
• Familiarity with distributed data processing or feature management platforms.