3 days ago

Associate Director, Software Engineering (Guardrail Platform AI Safety Track)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 17 hours agoStatus: Live

Job Summary

Lead the design, development, and productionization of AI safety guardrail detectors for enterprise AI workloads. Build detector pipelines using rule-based, pattern-matching, NLP/ML, embeddings, and LLM-as-a-Judge approaches, then optimize evaluation workflows and model thresholds. Integrate open-source and third-party safety solutions, implement end-to-end protection patterns (including RAG and agents), and deliver safety observability, governance, and cross-team rollout of scalable solutions.

Location: Shenzhen, Guangzhou, Xi'an

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Director level

Key Responsibilities

•Design, develop, and productionize AI safety detectors for enterprise AI applications, covering injection/jailbreak, PII and sensitive data, data leakage, harmful content, policy violations, and agent/tool-use risk controls.
•Build detector pipelines using rule-based detection, pattern matching, NLP/ML classifiers, embedding base models, LLM-as-a-Judge evaluators, and hybrid strategies with confidence scoring and policy-driven actions.
•Develop and optimize guardrail detector models and evaluation workflows, including test set creation, labeling strategies, fine-tuning, validation, threshold calibration, precision/recall optimization, and regression testing.
•Evaluate, integrate, and benchmark industry and open-source AI safety solutions, performing build-vs-buy analysis and production readiness assessment.
•Create end-to-end AI safety protection patterns across enterprise AI workloads (RAG, coding assistants, conversational AI, and agent layers), and implement safety observability and governance; partner with platform, infrastructure, security, and application teams for scalable rollout and lifecycle management.

Key Requirements

•Experience developing first-party AI safety detectors, including prompt injection/jailbreak, PII, data leakage, toxicity, policy violation, and agent safety detection.
•Experience building fine-tuning pipelines for safety-oriented LLMs/SMALL language models, including dataset curation, labeling, training workflow implementation, evaluation design, and production validation.
•Experience identifying, evaluating, integrating, and productionizing third-party or open-source AI safety detector solutions with judgment on quality, latency, cost, operational fit, and governance requirements.
•Experience making build-vs-buy decisions for detector capabilities and taking solutions through evaluation, integration, rollout, and ongoing production operations.
•Experience with AI evaluation or observability tools such as Langfuse, LangSmith, Arize, Phoenix, or similar platforms.

Tech Stack:AI safety detectorsPrompt injection detectionJailbreak detectionPII detectionData leakage preventionNLPMLEmbeddingsLLM-as-a-JudgeRAGCoding assistantsConversational AIAgent applicationDetector telemetryTracingDashboardsAudit trailsLangfuseLangSmithArize

Company Brief

HSBC

Global banking and financial services organisation offering retail, commercial, corporate and investment banking, wealth management, and global markets services across Europe, Asia, the Americas and the Middle East.

Industry: Banking

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: London, United Kingdom

Founded: 1865

Glassdoor: 3.6

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

HSBC

3 days ago

Associate Director, Software Engineering (Guardrail Platform AI Safety Track)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 17 hours agoStatus: Live

Job Summary

Location: Shenzhen, Guangzhou, Xi'an

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Director level

Key Responsibilities

•Design, develop, and productionize AI safety detectors for enterprise AI applications, covering injection/jailbreak, PII and sensitive data, data leakage, harmful content, policy violations, and agent/tool-use risk controls.
•Build detector pipelines using rule-based detection, pattern matching, NLP/ML classifiers, embedding base models, LLM-as-a-Judge evaluators, and hybrid strategies with confidence scoring and policy-driven actions.
•Develop and optimize guardrail detector models and evaluation workflows, including test set creation, labeling strategies, fine-tuning, validation, threshold calibration, precision/recall optimization, and regression testing.
•Evaluate, integrate, and benchmark industry and open-source AI safety solutions, performing build-vs-buy analysis and production readiness assessment.
•Create end-to-end AI safety protection patterns across enterprise AI workloads (RAG, coding assistants, conversational AI, and agent layers), and implement safety observability and governance; partner with platform, infrastructure, security, and application teams for scalable rollout and lifecycle management.

Key Requirements

•Experience developing first-party AI safety detectors, including prompt injection/jailbreak, PII, data leakage, toxicity, policy violation, and agent safety detection.
•Experience building fine-tuning pipelines for safety-oriented LLMs/SMALL language models, including dataset curation, labeling, training workflow implementation, evaluation design, and production validation.
•Experience identifying, evaluating, integrating, and productionizing third-party or open-source AI safety detector solutions with judgment on quality, latency, cost, operational fit, and governance requirements.
•Experience making build-vs-buy decisions for detector capabilities and taking solutions through evaluation, integration, rollout, and ongoing production operations.
•Experience with AI evaluation or observability tools such as Langfuse, LangSmith, Arize, Phoenix, or similar platforms.

Company Brief

HSBC

Industry: Banking

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: London, United Kingdom

Founded: 1865

Glassdoor: 3.6

Website LinkedIn