Sr. Software Engineer, Machine Learning, tvScientific

About Pinterest & tvScientific: Millions of people around the world visit Pinterest to discover creative ideas, dream about new possibilities, and plan for memories that last a lifetime. In an ambitious partnership to expand monetization capabilities, Pinterest is scaling tvScientific—the first and only Connected TV (CTV) advertising platform purpose-built for performance marketers. By leveraging massive data layers and cutting-edge data science, tvScientific unifies media buying, campaign optimization, measurement, and causal attribution into a single, highly automated CTV performance network trusted by global brands to scale real business outcomes across ecosystems like Hulu, Pluto TV, Disney+, and HBO Max.

Position Overview

We are seeking a highly autonomous, math-fluent, and code-proficient Sr. Software Engineer, Machine Learning, tvScientific to lead the technical development of our high-volume programmatic bidding and predictive optimization systems under a flexible remote or San Francisco hub configuration. In this high-leverage machine learning seat, you will claim end-to-end engineering ownership over real-time ad buying models capable of processing millions of bid decisions per second. Shifting completely away from routine non-regulated administrative data transcription logs, generic promotional content writing, or basic web layout configurations, you will run an active algorithmic optimization, multi-agent LLM workflow acceleration, and incrementality measurement laboratory. Partnering directly with distributed data engineering cells, you will translate real-world ad verification gaps into stable statistical products. This position requires an engineering authority with 4+ years of industrial history who structures algorithmic pipelines fluidly natively using Machine Learning and python primitives, commands deep familiarity with causal inference models, and optimizes low-latency adtech systems under production criteria.

Key Responsibilities

• Programmatic Bidding System Governance: Architect, implement, and maintain low-latency algorithmic bidding networks capable of handling millions of real-time programmatic ad decisions per second natively utilizing Machine Learning principles.
• Production Model Deployment & Orchestration: Train, serve, and monitor predictive ML models that optimize ad selection, click-through rates, and pricing matrices across the Connected TV (CTV) ecosystem.
• Causal Inference & Incrementality Instrumentation: Design and scale advanced measurement systems—including uplift modeling, synthetic controls, and difference-in-differences parameters—to prove the true causal lift of ad spend.
• Full Ad-Buying Lifecycle Customization: Formulate new data-driven products across the advertising spectrum, spanning audience targeting profiles, intelligent spend pacing, and multi-touch attribution layers.
• AI-Assisted Workflow Engineering: Integrate Large Language Models (LLMs) and agentic developer toolchains into the internal pipeline to accelerate systemic testing, debugging, and code refactoring.
• Distributed Technical Mentorship: Serve as a senior technical lead, providing clear code reviews, architectural feedback, and technical mentorship across a distributed software engineering team.
• Big Data Pipeline Collaboration: Partner with data engineering squads to ingest and manipulate massive, disparate real-time datasets utilizing cloud clusters.

Required Skills & Qualifications

• Possess a formal Bachelor’s degree in Computer Science, Mathematics, Engineering, or a matching highly quantitative discipline (or equivalent practical professional experience).
• A minimum of 4+ years of proven, successful industrial history operating inside a Senior Machine Learning Engineer, AdTech Platform Developer, Causal Inference Analyst, programmatic software engineer, or matching technical data capacity.
• Expert Production Python Command: Advanced, hands-on experience writing maintainable Python code optimized for live, high-concurrency production runtimes rather than static notebooks.
• Grounded mastery of statistical fundamentals, trial evaluation protocols, and experiment design, with a strong ability to reason when simple statistical baselines beat complex neural structures.
• Outstanding written, verbal, and analytical presentation communication strengths in English, with an established history making decisions and mapping architectures via text documentation across distributed cells.
• Location Context: Position operates under remote guidelines open exclusively to qualified US-based applicants , with optional access to our corporate hub in San Francisco, California .

Preferred Strategic Indicators (Nice to Have)

• Prior technical or functional engineering background operating inside high-volume AdTech or CTV platforms , managing Real-Time Bidding (RTB), supply-path optimization (SPO), or ad verification layers.
• Experience using advanced AI coding assistants (such as Cursor, GitHub Copilot, or Codex ) or LLM productivity tools for documentation searches and data exploration.
• Familiarity with Reinforcement Learning (RL), multi-armed bandit algorithms, big data computing tools ( Scala, Apache Spark ), or low-level systems programming tools ( Zig, C++, Rust ).
• Hands-on MLOps pipeline orchestration, model tracking, and cluster provisioning inside an AWS cloud ecosystem.

What We Offer

• Top-Tier US Technology Enterprise Compensation: A highly competitive annual base salary structure of $155,584—$320,320 USD calibrated to your machine learning trajectory, supplemented by lucrative corporate equity grants and comprehensive incentive bonuses.
• Flexible remote workspace infrastructure autonomy anywhere within the United States via our innovative PinFlex working model.
• Direct Macro Media Optimization Footprint: Elite professional credentials built by commanding the primary predictive models behind a category-defining CTV performance advertising platform.
• Comprehensive health care preservation benefits, including high-tier medical, dental, and vision insurance packages for engineers and their families.
• Access to robust continuous training resource channels, equity wealth management frameworks, generous paid time-off provisions, mental/physical wellness support networks, and an inclusive workplace culture designed to be equitable and inspiring.