AI Agent Engineer - Global Security Organization

he GSO provides industry-leading security and privacy services to Bytedance, guided by four principles: trust and transparency, business enablement, risk-informed decision-making, and proactive risk reduction. We strive to build sustainable, world-class security capabilities.

SecOps Validation Team (STOV) is responsible for the tools and technologies that support the TikTok infrastructure. STOV oversees technical validation, security operations, and drives engineering enhancements, including the deployment, configuration, and maintenance of security technologies across various domains.

STOV team is building domain specific AI applications to scale GSO's technical control compliance abilities. This role will work closely with STOV's product security to build AI agents which integrate with TikTok's CI/CD pipeline, providing TikTok product and development team with shift-left technical control review and implementation instructions.

As the AI agent engineer, you will be responsible for the entire agent development lifecycle. Your core focus will be on building robust and effective agents that deliver tangible value to our users.

• Use-Case Scoping and Design: Collaborate with product and design teams to identify high-impact use cases for AI agents. Define agent capabilities, goals, and success criteria based on user needs.
• Tool Integration and Development: Design, build, and maintain the APIs and functions that agents use to interact with the world. This includes integrating with ByteDance internal services, APIs, and creating GSO customized tools from scratch.
• Planning and Orchestration: Develop the core logic that allows agents to reason and create effective plans. You will implement and refine orchestration patterns, whether using ByteDance internal AI frameworks or by building custom agent runtimes.
• Reliability and Safety: Implement robust guardrails and safety mechanisms to ensure agents operate predictably and securely. This includes error handling, retry logic, and preventing unintended actions.
• Evaluation and Testing: Create comprehensive evaluation frameworks and automated testing suites to measure agent performance. You will define and track key metrics to drive continuous improvement.
• Memory and Retrieval-Augmented Generation (RAG): Implement and optimize memory systems that allow agents to learn from past interactions. You will build and fine-tune RAG pipelines to provide agents with relevant, up-to-date context from knowledge bases.
• Performance and Cost Optimization: Analyze and optimize the latency, token usage, and computational cost of agent operations. You will balance performance with accuracy to ensure a scalable and cost-effective system.
• Observability and Monitoring: Instrument agents with detailed logging, metrics, and tracing to provide deep visibility into their reasoning processes and actions. You will build dashboards and alerts to monitor agent health and performance.
• Collaboration and Communication: Clearly articulate complex technical concepts to both technical and non-technical stakeholders. You will work closely with your team to share knowledge, review code, and contribute to our engineering culture.

Qualifications

Minimum Qualifications

• Core Programming Skills: Proficiency in Python and a strong foundation in software engineering principles, including data structures, algorithms, and object-oriented design.
• LLM and Agent Frameworks: Hands-on experience building with LLMs and familiarity with agent development frameworks (e.g., LangChain, AutoGen, CrewAI, Semantic Kernel) or experience building custom agent architectures.
• Retrieval and Vector Databases: Practical experience with RAG, including vector embeddings, vector stores (e.g., Pinecone, Chroma, FAISS), and retrieval strategies.
• API and Tool Design: Experience designing, building, and consuming RESTful APIs and other web services.
• Infrastructure and DevOps: Familiarity with modern infrastructure and deployment tools, including Docker, Kubernetes, and CI/CD pipelines.
• Observability: Experience with logging, metrics, and tracing frameworks (e.g., Prometheus, Grafana, OpenTelemetry).
• Communication and Collaboration: Excellent written and verbal communication skills, with the ability to work effectively in a collaborative team environment.

Preferred Qualifications

• Bachelor's degree in Computer Science
• Multi-Agent Systems: Experience designing or building systems where multiple agents collaborate to solve a problem.
• Advanced RAG Pipelines: Experience building and optimizing complex RAG systems, including techniques like re-ranking, query transformation, and graph-based retrieval.
• Prompt Engineering and Fine-Tuning: Expertise in advanced prompt engineering and experience fine-tuning smaller, specialized language models for specific tasks.
• Production Experience: A track record of shipping and scaling agent-based features or products to a large user base.

Job Information

[For Pay Transparency] Compensation Description (annually)

The base salary range for this position in the selected city is $156000 - $316800 annually.

Compensation may vary outside of this range depending on a number of factors, including a candidate's qualifications, skills, competencies and experience, and location. Base pay is one part of the Total Package that is provided to compensate and recognize employees for their work, and this role may be eligible for additional discretionary bonuses/incentives, and restricted stock units.

Benefits may vary depending on the nature of employment and the country work location. Employees have day one access to medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, short-term and long-term disability coverage, life insurance, wellbeing benefits, among others. Employees also receive 10 paid holidays per year, 10 paid sick days per year and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).

The Company reserves the right to modify or change these benefits programs at any time, with or without notice.

For Los Angeles County (unincorporated) Candidates:

Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Our company believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment:

1. Interacting and occasionally having unsupervised contact with internal/external clients and/or colleagues;

2. Appropriately handling and managing confidential information including proprietary and trade secret information and access to information technology systems; and

3. Exercising sound judgment.