Note: The job is a remote job and is open to candidates in USA. OVA.Work is seeking an AI Reliability Engineer to ensure the reliability, availability, scalability, and operational excellence of AI and machine learning systems in production. The role involves combining Site Reliability Engineering, MLOps, and cloud engineering practices to build resilient AI platforms and improve system reliability.
Responsibilities
- Design and implement reliability engineering practices for AI and machine learning platforms
- Monitor the availability, latency, throughput, and health of AI services and model inference endpoints
- Develop Service Level Indicators (SLIs), Service Level Objectives (SLOs), and Service Level Agreements (SLAs) for AI systems
- Build automated monitoring, alerting, incident response, and self-healing capabilities
- Improve the reliability, scalability, and resilience of AI infrastructure and model-serving platforms
- Collaborate with AI Engineers, Data Scientists, Platform Engineers, DevOps Engineers, and Software Engineers to enhance production stability
- Automate operational tasks using scripting and Infrastructure as Code (IaC)
- Support deployment, rollback, and release strategies for AI services
- Investigate production incidents, conduct root cause analysis (RCA), and implement preventive measures
- Monitor model performance, data quality, model drift, and inference reliability
- Optimize cloud infrastructure, GPU utilization, and resource efficiency
- Implement disaster recovery, backup, failover, and business continuity strategies
- Ensure compliance with security, governance, and operational best practices
- Develop operational dashboards, runbooks, and reliability metrics
Skills
- Bachelor's or Master's degree in Computer Science, Engineering, Information Technology, or a related field
- 4+ years of experience in Site Reliability Engineering (SRE), DevOps, Platform Engineering, Cloud Engineering, or MLOps
- Experience supporting AI or machine learning applications in production
- Strong programming skills in Python, Go, or Bash
- Hands-on experience with Linux administration
- Experience with Docker and Kubernetes
- Experience with AWS, Microsoft Azure, or Google Cloud Platform
- Experience with CI/CD tools such as GitHub Actions, GitLab CI, Azure DevOps, or Jenkins
- Experience with Infrastructure as Code tools such as Terraform or Pulumi
- Strong understanding of distributed systems, networking, and cloud architecture
- Experience with monitoring and observability platforms such as Prometheus, Grafana, OpenTelemetry, ELK Stack, Datadog, or Splunk
- Experience with MLOps platforms such as MLflow, Kubeflow, SageMaker, Vertex AI, or Azure Machine Learning
- Experience supporting Large Language Models (LLMs) and Generative AI applications
- Knowledge of model serving technologies such as KServe, NVIDIA Triton Inference Server, Ray Serve, or BentoML
- Experience implementing AI model monitoring, drift detection, and performance analytics
- Familiarity with vector databases and Retrieval-Augmented Generation (RAG) architectures
- Experience with GPU infrastructure and inference optimization
- Knowledge of chaos engineering and resilience testing
- Understanding of Responsible AI, governance, and operational compliance
Company Overview