3 hours ago
Responsibilities
- Design, build, deploy, and operate machine learning models for fraud, scams, account takeover, payment abuse, transaction monitoring, and other financial-risk use cases.
- Own production ML systems end to end, including feature pipelines, training workflows, model serving, decision integrations, monitoring, alerting, drift detection, retraining, and incident response.
- Partner with risk strategy, product, and operations teams to turn models into approval, rejection, review, restriction, and other risk-mitigation controls.
- Build production LLM agents and agent architectures using tool calling, retrieval-augmented generation, workflow orchestration, structured outputs, memory, guardrails, and human review.
- Develop LLM-agent evaluation and reliability frameworks covering accuracy, task completion, consistency, latency, cost, reviewer acceptance, grounding, permissions, and failure handling.
- Ensure models and agents are explainable, traceable, secure, privacy-preserving, auditable, and appropriate for regulated risk environments.
- Use LLM-assisted development for implementation, testing, debugging, analysis, and documentation while maintaining security and review standards.
Requirements
- Significant professional experience in machine learning engineering, applied data science, or a closely related field, with a record of taking models from prototype to production.
- Strong Python skills and hands-on experience with machine learning frameworks such as PyTorch, TensorFlow, XGBoost, LightGBM, or scikit-learn.
- Knowledge of supervised learning, anomaly detection, representation learning, class-imbalanced modeling, model calibration, and evaluation under changing data distributions.
- Demonstrable fluency with LLM coding tools and experience building AI-integrated workflows or applications, including awareness of security, reliability, and governance risks.
- Familiarity with model explainability techniques including SHAP, feature attribution, reason-code generation, and model scorecards.
- Hands-on experience designing and deploying production LLM agents with agentic workflows, tool calling, retrieval-augmented generation, prompt and context management, structured outputs, and multi-step orchestration.
- Experience integrating LLM agents with internal systems, APIs, databases, search tools, case-management platforms, or decision engines.
- Understanding of LLM-agent evaluation and reliability, including hallucination control, grounding, observability, permissions, failure handling, human review, latency, and cost optimization.
- Experience with AI agents for fraud, risk, compliance, customer operations, cybersecurity, or other high-stakes domains is advantageous.
- Strong communication and collaboration skills across engineering, data science, risk, product, operations, legal, and compliance teams.
Categories
About OKX
OKX builds a global cryptocurrency exchange and Web3 wallet used by retail and institutional traders for spot, derivatives, and DeFi access, with developer APIs. Its business model centers on trading and financing fees, plus wallet and on-chain services. Founded in 2017 and privately held, OKX publishes monthly proof-of-reserves and operates as part of the OKG group serving crypto markets worldwide.