Overview
AI and Security Process Engineer focused on Agentic Systems on the USDS FUSE Intelligence team. This role designs, builds, and deploys autonomous AI agents that can reason, plan, and execute tasks to support a mature security organization protecting TikTok US data. You will work with Large Language Models (LLMs) and agentic frameworks to automate workflows, solve security problems, and interact with digital environments dynamically. Requires a blend of software engineering skills, LLM knowledge, and a creative approach to building autonomous systems for security and analytics.
The position is part of a hybrid team structure with in-office requirements of 3 days per week or as directed by management; scheduling may change over time.
Responsibilities
- Design and Develop AI Agents: Architect, build, and deploy robust, multi-step AI agents capable of complex reasoning, tool use, and decision-making using frameworks like LangChain, AutoGen, or CrewAI. Develop and integrate agentic systems using LLMs, RAG, and tool-use/function-calling frameworks to automate or accelerate complex tasks for end-users.
- RAG: Deep, practical experience with the end-to-end RAG lifecycle, from designing chunking and hybrid retrieval strategies for domain-specific data to implementing agentic design patterns.
- Workflow and Process Design: Translate user needs into robust, autonomous workflows that reason, plan, and execute actions.
- Integrate Tools and Data Sources: Enable agents to interact with external systems by integrating APIs, databases, and other data sources for real-world action and information retrieval.
- Implement Agentic Architectures: Develop and implement advanced agentic patterns such as ReAct (Reasoning and Acting), plan-and-execute, and multi-agent collaboration to solve complex, open-ended problems.
- Optimize and Evaluate Performance: Establish metrics to evaluate agent performance, reliability, and efficiency; iterate on design, prompting strategies, and model choice.
- LLM Customization: Fine-tune and adapt foundational LLMs for agentic tasks and domains; implement and refine Retrieval-Augmented Generation (RAG) pipelines to provide relevant context. Demonstrated experience building and shipping applications powered by LLMs.
- Collaboration: Work with product managers, data scientists, and other engineers to define requirements, identify automation opportunities, and integrate agentic solutions into core products and internal workflows.
- Stay Current: Maintain knowledge of advances in agentic AI, LLMs, and autonomous systems, and promote adoption of new techniques within the team.
Qualifications
- Minimum Qualifications: Bachelor’s or Master’s degree in Computer Science, AI, Machine Learning, or a related technical field.
- 5+ years of professional experience in software engineering or machine learning roles.
- Proven experience building and deploying solutions using agentic AI frameworks (e.g., LangChain, LlamaIndex, AutoGen) with a strong project portfolio.
- Deep understanding of LLMs, transformer architectures, and NLP techniques including prompt engineering, fine-tuning, and RAG.
- Solid Python fundamentals, production APIs, and experience with ML libraries (PyTorch, Hugging Face, Scikit-learn).
- Experience with APIs, databases, and cloud platforms (AWS, GCP, or Azure).
- Preferred Qualifications: Experience designing multi-agent systems with agent collaboration or competition; published AI/ML research; MLOps practices (Docker, Kubernetes, CI/CD); passion for autonomous agents; experience with automated tools in Java, C, or PowerShell and SQL.
About USDS
TikTok is the leading destination for short-form mobile video. U.S. Data Security (“USDS”) is a subsidiary of TikTok in the U.S., focused on governance of data protection policies and content assurance to keep U.S. users safe. The USDS teams span Trust & Safety, Security & Privacy, Engineering, User & Product Ops, Corporate Functions, and more.
Data Security Statement
This role requires the ability to work with systems designed to protect sensitive data and information and is subject to national security-related screening.
Why Join Us
We value creativity, curiosity, humility, and impact. Join a diverse, global team committed to innovation and growth in a rapidly evolving tech company.
USDS Reasonable Accommodation
USDS provides reasonable accommodations in our recruitment processes for candidates with disabilities or other protected reasons. If you need assistance, please reach out to us.
#J-18808-Ljbffr