Applied AI Engineer, Forensics - Global Security Organization

The mission of TikTok's Global Security Organization is to build and earn trust by reducing risk and securing our businesses and products. Also known as "GSO", this team is the foundation of our efforts to keep TikTok safe, secure, and operating at scale for over 1 billion people around the world. We work to ensure that the TikTok platform is safe and secure, that our users' experience and their data remains safe from external or internal threats, and that we comply with global regulations wherever TikTok operates.

Trust is one of TikTok's biggest initiatives, and security is integral to our success. In whatever ways users interact with us — whether they're watching videos on their For You page, interacting with a Live video, or buying products on TikTok Shop — GSO protects their data and privacy, so they can have a secure and trustworthy experience.

TikTok’s Global Forensics team is responsible for the company’s technical investigations and digital forensics work. This role sits at the intersection of applied AI, software engineering, security data engineering, and digital forensics. You will build evidence-aware AI systems that help investigators retrieve, correlate, reason over, package, and explain evidence across complex enterprise telemetry, while preserving auditability, reproducibility, privacy, and human judgment.

You will also partner closely with investigators to convert recurring case patterns into reusable workflows, AI-assisted investigation tools, evaluation datasets, playbooks, and detection/control improvements.

Responsibilities:

• Design and build AI-native forensic investigation workflows for evidence retrieval, enrichment, entity normalization, timeline reconstruction, evidence indexing, evidence packaging, and investigation report generation.
• Build agentic systems that safely interact with internal tools, APIs, logs, and investigation datasets through controlled tool use, permissioning, human-in-the-loop review, and auditable execution traces.
• Develop retrieval, knowledge, and reasoning systems over cases, logs, policies, tickets, reports, and evidence repositories, with grounded citations and structured outputs.
• Create evaluation frameworks for forensic AI workflows, including golden cases, regression tests, grounding checks, hallucination/failure analysis, precision/recall measurement, and investigator feedback loops.
• Engineer data workflows across platform audit logs, identity/cloud logs, endpoint/server telemetry, network logs, DLP, and other investigation data sources.
• Partner with forensic investigators to turn ambiguous investigative questions into reproducible workflows, reusable query packs, dashboards, agent tools, and defensible technical outputs.
• Drive proactive risk discovery by generalizing patterns from real cases, running targeted hunts across multi-source telemetry, validating signals, and converting findings into detection, logging, control, and process improvements.
• Apply AI-assisted engineering responsibly to accelerate prototyping, refactoring, testing, and documentation while maintaining code review, test coverage, change control, privacy safeguards, and evidentiary defensibility.

Qualifications Minimum Qualifications:

• Strong hands-on software engineering ability in Python, plus experience with Go, TypeScript, Java, or another production language.
• Hands-on experience building LLM-powered applications, agentic workflows, RAG/retrieval systems, tool/function calling, structured generation, or evaluation frameworks.
• Experience querying, processing, and correlating large-scale security, operational, or enterprise telemetry across multiple data sources.
• Ability to design reliable, testable, observable, and auditable systems for high-stakes investigation workflows.
• Working knowledge of digital forensics, technical investigations, incident response, threat hunting, insider risk, data misuse investigations, or enterprise security operations.

Preferred Qualifications:

• Experience building investigation platforms, forensic tooling, analyst workbenches, detection engineering platforms, security data products, or investigation workflow systems.
• Experience with LangGraph, LlamaIndex, LangChain, MCP, vector databases, hybrid search, reranking, knowledge graphs, or custom agent orchestration.
• Familiarity with AI security risks such as prompt injection, tool misuse, data leakage, unsafe autonomous actions, model/output provenance, and agent sandboxing.
• Experience with cross-domain investigations combining DLP, identity/cloud, endpoint/EDR/HIDS, network telemetry, internal platform audit logs, and business context.