AI Application Architect
OKX is a leading global cryptocurrency exchange offering a wide range of trading services, including spot and derivatives trading, as well as Web3 solutions.
Investors
Projects
About OKX
OKX is a global cryptocurrency exchange known for its trading services and financial products. The platform offers a wide range of features, including spot and derivatives trading, staking services, and a user-friendly interface suitable for both beginners and experienced traders.
Skills
About the Role
You will design and build AI applications for SRE and DevOps use cases, including fault detection, change analysis, capacity risk identification, automated inspections, drill evaluation, and recovery recommendations. You will develop automated root-cause analysis and AIOps capabilities, and embed AI into engineering and incident-response workflows.
Requirements
- Bachelor's degree or above in Computer Science or a related field.
- 8+ years of experience in R&D, architecture, or platform engineering.
- Strong software architecture skills in microservices, distributed systems, high-availability design, service governance, observability, and platform engineering.
- Knowledge of LLM application development, RAG, Embedding, vector databases, Agents, Function Calling, Tool Calling, and Prompt Engineering.
- Experience delivering AI Agent or intelligent assistant products.
- Experience with RCA or AIOps capability development.
- Proficiency in Java, Python, Go, or TypeScript.
- Knowledge of Kubernetes, Docker, Kafka, Redis, MySQL, Elasticsearch, Prometheus, Grafana, and OpenTelemetry.
- Current right to work in Singapore without requiring visa sponsorship.
Responsibilities
- Design and build AI Harness capabilities for SRE and DevOps scenarios.
- Develop an automated root cause analysis system using logs, metrics, tracing, events, changes, and topology data.
- Build AIOps capabilities for alert noise reduction, anomaly detection, event correlation, trend prediction, fault attribution, and automated remediation.
- Collaborate with R&D, SRE, platform, data, and business stakeholders to embed AI into Code Review, CI/CD, GitOps, DevOps, incident response, and stability governance processes.
Benefits
- Wellness allowance.
- Meal allowance.
- Comprehensive healthcare schemes for employees and dependents.
- Team-building programs and company events.
