Machine Learning Engineer - TikTok BRIC Live Integrity - Singapore

TikTok; Singapore; On-site; SGD 120,000 - 190,000; Full time

Job summary

TikTok is seeking an AI risk scientist to lead detection and mitigation of ecosystem and financial risks on TikTok Live, a platform serving hundreds of millions of users.

You will design high‑precision, low‑latency risk models using multimodal data, study adversarial patterns, and build robust defenses with AI Agents, LLM fine‑tuning, and multimodal reasoning to improve risk scoring and decision making across global markets.

Qualifications

• Bachelor’s degree or higher in Computer Science, Mathematics, Statistics, or a related field.
• Solid background in machine learning and deep learning; proficiency in classification, clustering, and sequence modeling algorithms (e.g., XGBoost, DeepFM, Transformers).
• Strong coding proficiency in Python, C++, or Go; experience with mainstream frameworks like TensorFlow or PyTorch; experience with large‑scale distributed systems.

Responsibilities

• Risk Identification & Governance: Lead the detection and mitigation of ecosystem/content risks and financial risks on TikTok Live.
• Model Development: Design and optimize high‑precision, low‑latency risk detection models utilizing massive multimodal data (text, image, audio, and behavioral sequences).
• Adversarial Defense: Analyze black‑market tactics and attack patterns to design robust defense strategies and respond rapidly to emerging threats.
• Advanced AI Application: Drive the adoption of cutting‑edge technologies, including AI Agents, LLM Fine‑tuning, and Multimodal Models, to enhance automated reasoning and decision‑making capabilities in complex risk scenarios.

Skills

Machine learning

Deep learning

XGBoost

DeepFM

Transformers

Python

C++

Go

TensorFlow

PyTorch

Distributed systems

Communication & teamwork

Education

Bachelor’s degree or higher in Computer Science/Math/Statistics

Tools

Python

C++

Go

TensorFlow

PyTorch

Job description

Responsibilities

TikTok Live is a world-leading live streaming platform serving hundreds of millions of users globally. By joining us, you will step into one of the industry's most challenging environments, characterized by massive scale, high concurrency, and complex global adversarial scenarios.

This role offers immense potential for professional growth and the opportunity to apply cutting‑edge AI technologies in real‑world applications. You will protect the safety and financial security of our global community, setting new benchmarks for industry risk control.

• Risk Identification & Governance: Lead the detection and mitigation of ecosystem/content risks and financial risks on TikTok Live.
• Model Development: Design and optimize high‑precision, low‑latency risk detection models utilizing massive multimodal data (text, image, audio, and behavioral sequences).
• Adversarial Defense: Analyze black‑market tactics and attack patterns to design robust defense strategies and respond rapidly to emerging threats.
• Advanced AI Application: Drive the adoption of cutting‑edge technologies, including AI Agents, LLM Fine‑tuning, and Multimodal Models, to enhance automated reasoning and decision‑making capabilities in complex risk scenarios.

Minimum Qualifications

• Bachelor’s degree or higher in Computer Science, Mathematics, Statistics, or a related field.
• Algorithmic Foundation: Solid background in machine learning and deep learning; proficiency in classification, clustering, and sequence modeling algorithms (e.g., XGBoost, DeepFM, Transformers).
• Engineering Skills: Strong coding proficiency in Python, C++, or Go. Experience with mainstream frameworks like TensorFlow or PyTorch. Experience with large‑scale distributed systems is a strong plus.
• Strong logical thinking and data sensitivity. Demonstrated passion for risk control and adversarial challenges. Excellent communication and teamwork skills.

Preferred Qualifications

• AI Agent Experience: Proven track record in building AI Agents for complex task planning, tool use, or autonomous decision‑making.
• LLM Expertise: Hands‑on experience with LLM fine‑tuning techniques such as SFT and RLHF; experience applying Large Language Models to vertical domains.
• Multimodal Capabilities: Deep understanding of multimodal representation learning, video understanding, or cross‑modal retrieval.
• Domain Experience: Prior experience in community content safety, trust & safety (T&S), or anti‑fraud.

About TikTok

TikTok is the leading destination for short‑form mobile video. At TikTok, our mission is to inspire creativity and bring joy. TikTok's global headquarters are in Los Angeles and Singapore, and we also have offices in New York City, London, Dublin, Paris, Berlin, Dubai, Jakarta, Seoul, and Tokyo.

Why Join Us

Inspiring creativity is at the core of TikTok's mission. Our innovative product is built to help people authentically express themselves, discover and connect - and our global, diverse teams make that possible. Together, we create value for our communities, inspire creativity and bring joy - a mission we work towards every day.

We strive to do great things with great people. We lead with curiosity, humility, and a desire to make impact in a rapidly growing tech company. Every challenge is an opportunity to learn and innovate as one team. We're resilient and embrace challenges as they come. By constantly iterating and fostering an "Always Day 1" mindset, we achieve meaningful breakthroughs for ourselves, our company, and our users. When we create and grow together, the possibilities are limitless. Join us.

Diversity & Inclusion

TikTok is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At TikTok, our mission is to inspire creativity and bring joy. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.