6 days ago
Guangzhou, ChinaStaff+
Responsibilities
- Design, develop, and productionize AI safety detectors for prompt injection, jailbreaks, personally identifiable information, sensitive data, harmful content, policy violations, system prompt leakage, and agent or tool-use risks.
- Build detector pipelines using rules, pattern matching, NLP and ML classifiers, embedding models, LLM-as-a-Judge evaluators, and hybrid detection strategies.
- Develop fine-tuning and evaluation workflows, including dataset creation, data labeling, model validation, threshold calibration, regression testing, and precision/recall optimization.
- Evaluate, benchmark, integrate, and productionize open-source and third-party AI safety solutions and make build-versus-buy decisions.
- Design end-to-end safety protections for RAG systems, coding assistants, conversational AI, and agent applications across input, retrieval, generation, output, logging, and tool-execution layers.
- Build AI safety observability and governance capabilities, including telemetry, tracing, dashboards, evaluation metrics, audit trails, feedback loops, and operational controls.
- Partner with AI platform, infrastructure, security, and application teams to optimize performance, scale solutions, manage detector lifecycles, and execute reliable rollouts.
Requirements
- Experience developing first-party AI safety detectors for prompt injection, jailbreaks, personally identifiable information, data leakage, toxicity, policy violations, or agent safety.
- Experience building fine-tuning pipelines for safety-oriented large or small language models, including dataset curation, labeling strategies, training workflows, evaluation design, and production validation.
- Experience evaluating, integrating, and productionizing third-party or open-source detector solutions based on quality, latency, cost, operational fit, and governance requirements.
- Experience making build-versus-buy decisions and taking internally developed or externally sourced detector solutions through production rollout and ongoing operation.
- Experience with AI evaluation or observability tools such as Langfuse, LangSmith, Arize, Phoenix, or similar platforms.
- Familiarity with data loss prevention, secret scanning, document classification, or enterprise information protection tooling.
- Experience with adversarial testing, red teaming, or continuous attack simulation for AI systems.
Benefits
- Flexible working and opportunities for continuous professional development and career growth.
- Inclusive and diverse workplace with equal opportunity employment.
- Location: Guangzhou or Xi'an.
Tech Stack
Phoenix
Categories
About HSBC
Opening up a world of opportunity for our customers, investors, ourselves and the planet. We're a financial services organisation that serves more than 40 million customers, ranging from individual savers and investors to some of the world’s biggest companies and governments. Our network covers 58 countries and territories, and we’re here to use our unique expertise, capabilities, breadth and perspectives to open up a world of opportunity for our customers. HSBC is listed on the London, Hong Kong, New York, and Bermuda stock exchanges. To view our social media terms and conditions please visit the following webpage: http://www.hsbc.com/social-TandCs