NewEra Inc. is an AI-first technology company specializing in digital transformation solutions for retail and enterprise partners. This role owns the engineering foundations that make AI delivery repeatable, observable, scalable, and cost-efficient. You will build the deployment and runtime capabilities, automation, and operational controls that allow AI teams to move from experiments to production safely — without rebuilding infrastructure for every new use case.
What you will do
- Design and maintain platform components used to build, deploy, and operate AI and ML applications
- Provide reusable patterns for model serving, LLM application deployment, secrets management, configuration, and environment promotion
- Build self-service workflows and templates that reduce the effort required to launch and maintain AI services
- Integrate AI workloads with NewEra's cloud, application, data, identity, and observability infrastructure
- Document platform interfaces, supported deployment patterns, operational limits, and ownership boundaries
- Implement automated build, test, evaluation, deployment, and rollback workflows for AI services and models
- Support versioning and traceability for model artefacts, prompts, configurations, datasets, and evaluation results
- Establish environment separation and release controls appropriate to the risk and criticality of each application
- Improve developer feedback loops so teams can identify failures before they affect users
- Instrument AI services for availability, latency, throughput, errors, token usage, resource utilisation, and other relevant signals
- Set and monitor service-level objectives with product and engineering owners
- Design for scaling, capacity management, rate limits, retries, timeouts, graceful degradation, and recovery
- Lead or support incident response for platform-related failures and ensure follow-up actions address root causes
- Implement appropriate identity, access, network, secret, and data-handling controls for AI workloads
- Track model and infrastructure costs by service or use case, and identify practical optimisation opportunities
- Support model routing, caching, batching, autoscaling, and provider selection where they improve cost or performance
- Evaluate managed services and open-source options based on reliability, total cost, portability, and operational burden
- Partner with AI engineers and product teams to understand friction in the development-to-production path
- Turn recurring deployment and operational problems into platform capabilities rather than one-off fixes
- Set clear support boundaries and provide practical runbooks, examples, and onboarding materials
What we are looking for
- 5+ years in platform engineering, DevOps/SRE, backend engineering, ML engineering, or a closely related discipline
- Strong programming and scripting skills, preferably Python plus a systems or cloud-oriented language
- Hands-on experience with cloud infrastructure, containers, orchestration, CI/CD, infrastructure as code, and observability
- Experience operating production APIs or services with measurable reliability, performance, and security requirements
- Understanding of model serving or AI application deployment, including LLM API integrations or ML model lifecycle practices
- Experience with secrets, access control, environment management, automated testing, and incident response
- Working proficiency in English for technical documentation and collaboration
Nice to have
- Experience with Kubernetes, Terraform, Docker, GitHub Actions, or equivalent CI/CD systems
- Experience with MLflow, model registries, feature stores, or dedicated model-serving infrastructure
- Experience operating LLM applications, vector databases, GPU workloads, or inference gateways
- Experience with OpenTelemetry, Prometheus, Grafana, or comparable observability tools
- Experience with multi-cloud or hybrid infrastructure and vendor/model-provider evaluation
What you get
- Competitive salary commensurate with experience
- Performance-based bonus
- Full statutory insurance coverage (BHXH, BHYT, BHTN) per Vietnamese labor law
- Ownership of a critical AI infrastructure function in a fast-scaling company
- Clear career growth path in Platform Engineering / AI Infrastructure