Machine Learning Engineer, E-commerce Governance Algorithms

ByteDance ByteDance · Big Tech · Seattle, WA · R&D

Machine Learning Engineer focused on e-commerce governance, using GNNs, LLMs, and time series for fraud detection, quality control, and logistics optimization. The role involves building and deploying AI solutions to improve platform health, seller compliance, and user trust.

What you'd actually do

  1. Build graph-powered risk networks to uncover similar product clusters and high-risk seller/creator groups in emerging markets, reducing false advertising incidents in global regions.
  2. Develop LLM-based multi-modal systems using cross-modal fusion (text, images, behavioral data) to detect false advertising and low-quality products. Deploy AI-powered product business suggestions to improve seller compliance and user trust.
  3. Lead time-series forecasting innovation for logistics performance metrics (e.g., delivery delays, cancellation rates), driving improvement in the e-commerce experience through predictive analytics.
  4. Develop multi-task models using MMoE and dynamic loss functions, driving measurable improvements in platform product, service, and logistics health.
  5. Optimize LLM reasoning with DPO/GRPO to enhance fraud detection, outperforming traditional SFT methods. Enhance tabular data modeling for better explainability in e-commerce risk assessments.

Skills

Required

  • Python
  • C++
  • PyTorch
  • TensorFlow
  • Graph Neural Networks
  • Time Series Analysis
  • LLM

Nice to have

  • Multi-Objective Optimization
  • Causal Inference
  • DPO/GRPO
  • Multi-modal systems
  • Cross-modal fusion
  • Tabular data modeling
  • Explainability

What the JD emphasized

  • 3+ years in anti-fraud, prediction/forecasting, e-commerce governance, or related fields.
  • Track record of delivering AI solutions with measurable business impact.

Other signals

  • LLMs
  • Graph Neural Networks
  • Time Series Prediction
  • Multi-Objective Optimization
  • Causal Inference
  • DPO/GRPO