• Design and implement end-to-end document intelligence pipelines on AWS • Develop and optimize ML models for document classification, segmentation, and field extraction • Build scalable data processing systems handling PDFs up to 2000 pages • Collaborate with subject matter experts to create and refine requirements for extraction • Own features from research through production deployment and monitoring • Establish evaluation frameworks and quality metrics for extraction accuracy

• Design and implement natural language query agents that translate user questions into optimized BigQuery SQL. • Build and operationalize Gemini-powered AI workflows for analytics, summarization, and forecasting. • Develop time-series forecasting models using BigQuery ML and integrate results with Gemini for explainability. • Implement governance, access control, and auditability for AI-driven data access. • Integrate AI capabilities into Microsoft Teams for seamless user adoption. • Collaborate with data engineering, security, and business teams to ensure scalable and secure solutions. • Optimize query performance, cost controls, and data reliability in BigQuery.

• Build and maintain the foundational AI gateways and inference services used across Kraken to provide reliable and efficient access to ML and generative AI models. • Architect and evolve internal evaluation tooling and monitoring frameworks that allow teams to measure the performance, quality, and safety of their systems at scale. • Act as a technical mentor by teaching software engineers and ML specialists how to adopt foundational capabilities, ensuring AI is easy to use and integrated into everyday development. • Create and maintain high-quality documentation, internal guidance, and technical standards to help teams understand when and how to use AI effectively. • Continuously improve Kraken's approach to AI enablement by balancing speed, cost, and quality within the infrastructure you manage.

This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description The Content Understanding team builds machine learning models that "read" Pinterest content—images, text, and video—to produce high-quality semantic signals (e.g., embeddings, localization, quality/safety labels). These signals power relevance and retrieval for Homefeed, Search, Related Pins, and Ads, and also support integrity use cases like spam and low-quality detection. We work end-to-end: from data and labeling strategy, to model training and evaluation, to low-latency serving and monitoring at Pinterest scale. The role is ideal for a senior modeler who also enjoys developing, productionizing models and leading technical direction across teams. - Lead modeling strategy for content understanding (vision, NLP, multimodal), including architecture selection, training approach, and evaluation methodology. - Design and ship production models that generate content signals such as embeddings and classifications used across multiple product surfaces. - Own the full ML lifecycle: data/labeling strategy (human labels + weak supervision), training pipelines, offline evaluation, online experimentation, deployment, and monitoring/retraining. - Partner with infra/platform teams to ensure scalable, reliable training/serving (latency, cost, observability, rollout safety). - Collaborate with signal-consuming teams (ranking, retrieval, integrity, ads) to define signal contracts, adoption patterns, and success metrics. - Provide technical leadership through design reviews, mentoring, and raising the quality bar for modeling and ML engineering practices. Qualifications - M.S/ PhD degree in Computer Science, Statistics or related field. - Significant industry experience building software and ML pipelines/systems, including technical leadership (project/tech lead or equivalent). - Strong proficiency in Python and at least one ML stack such as PyTorch / TensorFlow, plus solid software engineering fundamentals. - Proven experience training and deploying ML models to production, including model versioning, rollouts, monitoring, and retraining strategies. - Deep hands-on experience in content understanding domains, such as: - computer vision (classification, detection, representation learning), - NLP (text classification, entity/topic modeling), - multimodal / embedding models (e.g., transformer-based representations). - Experience working with large-scale datasets and distributed compute (e.g., Spark-like ecosystems, distributed training, GPU environments). - Strong applied skills in evaluation and experimentation: defining metrics, offline/online alignment, A/B testing, debugging regressions, and model quality analysis. - Demonstrated ability to influence across teams and drive ambiguous problem areas to measurable outcomes. Requirements - This position is not eligible for relocation assistance. - This role will need to be in the office for in-person collaboration 1-2 times/quarter and therefore can be situated anywhere in the country. Benefits - Visit our PinFlex page to learn more about our working model.