Jobs / EML
MLOps Engineer
EML · Sydney, NSW, Australia
Sydney, NSW, AustraliaFull timeExp: 2+ yrsHybrid
Remuneration
Annual incentive scheme, regular salary reviews, Fitness Passport, retailer and partner discounts, wellbeing program, learning and development, and employee assistance program.
Location
Sydney, NSW, Australia
Visa sponsorship
No visa sponsorship
Australian working rights without restriction
Job summary
The MLOps Engineer bridges machine learning development and production, building the infrastructure, pipelines, and processes needed to deliver reliable, scalable AI solutions in personal injury claims management. The role develops Python applications and FastAPI APIs, automates CI/CD with GitHub Actions, deploys LLM inference workloads using vLLM and Ray, and operates containerised services with Docker and Kubernetes.
Benefits
Reward and recognition programWork-from-home flexibility after probation, subject to performanceMonthly rostered days off or a 9-day fortnightFitness PassportRetailer, banking, superannuation, and private health insurance discountsCorporate wellbeing programLearning and developmentEmployee assistance programCompany-wide eventsAnnual incentive schemeRegular salary reviews
Qualifications
- Australian working rights without restriction.
- At least 2 years of experience as an MLOps Engineer or Software Engineer.
- Strong Python skills and hands-on experience building production-ready RESTful APIs with FastAPI.
- Experience with GitHub Actions CI/CD, containerisation, and Kubernetes application deployment and operations.
- Experience with Linux, Bash scripting, and deployment and operations automation.
- Experience deploying and serving LLMs with technologies such as vLLM and Ray.
- Knowledge of inference optimisation, prompt engineering, and LLM evaluation.
- Collaborative, solutions-focused approach and strong troubleshooting skills.
Responsibilities
- Design, develop, and maintain scalable Python applications, RESTful APIs, and AI solutions.
- Build and optimise GitHub Actions CI/CD pipelines for testing, deployment, and delivery.
- Deploy and optimise production LLM inference workloads using vLLM and Ray.
- Develop and maintain containerised applications with Docker and Kubernetes.
- Apply prompt engineering, LLM evaluation, and inference optimisation techniques.
- Collaborate with technology, AI, and business stakeholders to deliver secure, production-ready solutions.
Skills
BashDockerGitHubGitHub ActionsKubernetesLinuxMakePythonREST
Languages
Python
Work schedule
Full-timeMonthly rostered days off or a 9-day fortnight
Industry
Personal injury claims management
Contract length
12 months
Relocation
No