Minimum qualifications:- Bachelor's degree or equivalent practical experience.
- 2 years of experience programming in Python or C .
- 1 year of experience with one or more of the following: reinforcement learning (e.g., sequential decision making), natural language processing, ML infrastructure, or specialization in another ML field.
- 1 year of experience with end-to-end machine learning (e.g., model deployment, model evaluation, optimization, data processing, debugging).
Preferred qualifications:- Master's degree or PhD in Computer Science or related technical fields.
- 2 years of experience with data structures or algorithms.
- Experience developing accessible technologies.
- Experience with Ads.
About the jobThe Account Structure Intelligence (ASI) team's mission is to simplify the advertiser experience by transforming complex account management into an automated, AI-ready framework, empowering advertisers to capture all high-value traffic with minimal manual input.
On the ASI team, you will design and build the core LLM-powered extraction engine responsible for processing advertiser URLs. You will bridge advanced Generative AI and large-scale data infrastructure to parse unstructured web pages into structured, queryable inventory representations.
In this role, you will take ownership of end-to-end extraction workflows-from model exploration, training, and fine-tuning to building high-throughput batch and near-line production pipelines. You will collaborate with partner teams and fellow engineers to turn raw web content into high-fidelity signals that power customized ad creatives and landing page experiences across the entire Ads ecosystem.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $147000 - $210000 (USD) 15% bonus target equity benefits
Learn more about benefits at Google .
Responsibilities - Apply LLMs to information retrieval, entity extraction, and structured schema generation from semi-structured and unstructured web content.
- Collaborate with peers and stakeholders through design and code reviews to ensure best practices amongst available technologies (e.g., style guidelines, checking code in, accuracy, testability, and efficiency).
- Contribute to existing documentation or educational content and adapt content based on product/program updates and user feedback.
- Triage product or system issues and debug/track/resolve by analyzing the sources of issues and the impact on hardware, network, or service operations and quality.
- Experiment with and implement prompt engineering, supervised fine-tuning, distillation, and model compression techniques to optimize accuracy, throughput, and inference cost.
