Software Engineer III, Commerce Actor Safety, Intelligence

Written by the T&S Network from Google's posting.

Builds the machine learning and back-end systems behind the abuse intelligence stack that protects users and merchants on Google's shopping products. The Actor Safety team works on detecting spam, fraudulent and abusive actors across Commerce surfaces, covering detection models, agents and moderation platforms.

• Spam and platform abuse
• Fraud and scams

What you'd do

• Shape actor safety strategy with the PM and Eng leads, pairing abuse prevention frameworks with targeted tactical protections.
• Analyze complex abuse patterns and precision/recall metrics to improve detection models and operational workflows.
• Design, train, deploy and iterate on ML models, including Gemini LLMs, GNNs and NLP architectures, to detect spam, fraud and abusive behavior.
• Build data pipelines for training data curation, active learning workflows and synthetic datasets.
• Build LLM-as-a-judge evaluation frameworks for model monitoring and performance tracking.
• Create fast, fault-tolerant back-end services and an intelligence platform that manages models and ties into the actor lifecycle.

What it asks for

• Bachelor's degree or equivalent practical experience.
• 2+ years coding in Python or another language, or 1 year with an advanced degree.
• 2+ years of ML development and ML infrastructure work (model deployment, evaluation, data processing, debugging, fine-tuning) or large-scale data systems.
• Working knowledge of relational databases and SQL.
• Master's or PhD in Computer Science or a related technical field (preferred).
• 2+ years with data structures and algorithms (preferred).
• Experience with distributed infrastructure, storage or application frameworks such as Spanner (preferred).

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Googlenorth_east before you apply. If we got something wrong, report this listing.