Machine Learning Engineer, Global E-Commerce (ETA, Pricing & Conversion)

ByteDance; Singapore; On-site; SGD 140,000 - 200,000; Full time

Job summary

ByteDance is hiring in Singapore for a senior algorithmic role in its Global E-commerce Algorithm team, focusing on bridging physical fulfillment with digital user experience. You will build core AI, search, and recommendation systems that scale to millions of users and influence platform GMV.

Work includes ETA prediction, intelligent pricing, impression allocation, and LLM/AI agent innovations to push cutting-edge e-commerce capabilities and user growth.

Qualifications

• Master's or PhD in CS, Statistics, Mathematics, Operations Research, or a related highly quantitative field.
• Strong fundamentals in data structures and algorithms, with proficient programming skills in Python, C++, or Java.
• Experience with Big Data tools (e.g., Spark, Hive SQL) and Deep Learning frameworks (e.g., TensorFlow, PyTorch).
• Experience with A/B testing, experimentation design, and data-driven decision making.
• Demonstrated ability to translate complex, open-ended business problems into highly scalable algorithmic solutions.

Responsibilities

• Next-Gen ETA Prediction: Build and optimize end-to-end ETA prediction systems leveraging OneTrans Model; analyze spatio-temporal sequences to improve ETA accuracy and click-to-order rates.
• Intelligent Pricing via Causal Inference: Design and implement intelligent shipping-fee pricing and subsidy-pricing coordination using causal inference for multi-objective optimization.
• Conversion & Impression Allocation: Integrate fulfillment factors into core Search and Recommendation ranking algorithms to balance user experience and business costs.
• LLM & AI Agent Innovation: Develop domain-specific LLMs and AI agents using CPT, SFT, RL; deploy autonomous agents to diagnose and resolve complex issues.

Skills

Python

C++

Java

TensorFlow

PyTorch

A/B Testing

Experiment Design

Algorithmic Thinking

Big Data

Spark

Hive SQL

Education

Master's or PhD in Computer Science / Statistics / Mathematics / OR

Tools

Spark

Hive SQL

Job description

Responsibilities

About the Team The Global E-commerce Algorithm team is the core engine driving the ultimate shopping experience and user growth for our rapidly expanding international platform. At the intersection of entertainment and commerce, we are shaping the future of "Discovery E-Commerce" by building cutting-edge AI, search, and recommendation systems that connect millions of users with the products they love.

In this role, you will focus on solving massive-scale, consumer-facing challenges by bridging the gap between physical fulfillment and the digital user experience. You will build core algorithmic frameworks from the ground up, deeply integrating physical logistics factors—such as delivery speed, reliability, and shipping costs—into our core Search and Recommendation ecosystems. By dynamically optimizing impression allocation and conversion strategies, your work will directly drive user growth and platform GMV. You will push the boundaries of applied machine learning by leveraging cutting-edge techniques, including our proprietary OneTrans Model for ETA prediction, Causal Inference for dynamic pricing, and the latest advancements in Large Language Models (LLMs) and AI Agents.

Job Responsibilities

1. Next-Gen ETA Prediction: Build and optimize end-to-end Estimated Time of Arrival (ETA) prediction systems leveraging our proprietary OneTrans Model. Analyze spatio-temporal sequences using deep learning to improve ETA accuracy, enhance consumer trust, and boost click-to-order rates.
2. Intelligent Pricing via Causal Inference: Design and implement intelligent shipping-fee pricing, free-shipping strategies, and subsidy-pricing coordination. Utilize advanced Causal Inference techniques to build multi-objective optimization models that perfectly balance user landed price, platform costs, and profitability.
3. Conversion & Impression Allocation: Deeply integrate key fulfillment factors (e.g., delivery speed, shipping cost) into core Search and Recommendation ranking algorithms. Design intelligent impression allocation and dynamic consumer presentation strategies that balance user experience and business costs, ultimately driving higher retention and repeat purchase rates.
4. LLM & AI Agent Innovation: Pioneer the development of domain-specific LLMs by leveraging massive e-commerce data for Continual Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL). Design and deploy intelligent AI Agents based on an "Agent + Skill" framework to autonomously diagnose and resolve complex user-facing and operational issues.

Qualifications

Minimum Qualifications

• Master's or PhD degree in Computer Science, Statistics, Mathematics, Operations Research, or a related highly quantitative field.
• Solid foundation in data structures and algorithms, with proficient programming skills in Python, C++, or Java.
• Strong fundamentals in applied machine learning, with hands-on experience processing large-scale data using Big Data tools (e.g., Spark, Hive SQL) and Deep Learning frameworks (e.g., TensorFlow, PyTorch).
• Experience with A/B testing, experimentation design, and data-driven decision making.
• Demonstrated ability to translate complex, open-ended business problems into highly scalable algorithmic solutions.
• A strong passion for solving complex, high-impact e-commerce challenges and driving user growth.

Preferred Qualifications

• Deep expertise and industry experience in at least one of the following core areas:
  • Spatio-Temporal Modeling: Sequence prediction, ETA modeling, or graph neural networks.
  • Causal Inference: Dynamic pricing, uplift modeling, or user growth algorithms.
  • Search & Recommendation: RecSys ranking, computational advertising, or impression allocation.
  • LLM / Generative AI: LLM training pipelines (CPT, SFT, RLHF/RLAIF) and building Agentic workflows.
• A strong track record of algorithmic innovation, demonstrated by publications at top-tier conferences (e.g., KDD, NeurIPS, WWW, SIGIR, WSDM, ICLR, ICML).

About Us

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Lemon8, CapCut and Pico as well as platforms specific to the China market, including Toutiao, Douyin, and Xigua, ByteDance has made it easier and more fun for people to connect with, consume, and create content.

Why Join ByteDance

Inspiring creativity is at the core of ByteDance's mission. Our innovative products are 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 enrich life - a mission we work towards every day.

As ByteDancers, 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. 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

ByteDance 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 ByteDance, our mission is to inspire creativity and enrich life. 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.