Senior ML Scientist, Video Ads Personalization

Prime Video & Amazon MGM Studios; New York (NY); On-site; USD 184,000 - 249,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Prime Video Ads is seeking a senior ML scientist to advance personalized advertising using cutting-edge ML techniques at scale. You will own model development, experimental design, and cross-functional collaboration to optimize monetization and user experience.

You will work on deep learning models, causal inference, and production-ready systems, collaborating with PMs and engineers to deliver impact across hundreds of millions of customers.

Qualifications

• 3+ years of building machine learning models for business applications.
• PhD or Master’s degree with 6+ years of applied research experience.
• Proficiency in Java, C++, and Python.
• Experience with neural deep learning methods and ML.
• Experience with large-scale distributed systems (Hadoop, Spark).
• Experience with PyTorch or JAX for ML/AI development.

Responsibilities

• Lead ML model development for advertising decisions at scale.
• Design deep learning architectures for customer behavior prediction.
• Design and analyze large-scale A/B experiments using causal inference to measure impact.
• Collaborate with product managers to translate findings into product decisions.
• Shape the team’s scientific roadmap and high-impact research directions.
• Partner with engineering to meet production latency and scalability requirements.

Skills

ML model development

Deep learning

Java/C++/Python

Experimentation

Education

PhD or Master’s with 6+ years of applied research

Tools

Hadoop

Spark

PyTorch

JAX

Job description

Prime Video Ads is seeking a senior ML scientist to advance personalized advertising using cutting-edge ML techniques at scale. You will own model development, experimental design, and cross-functional collaboration to optimize monetization and user experience.

You will work on deep learning models, causal inference, and production-ready systems, collaborating with PMs and engineers to deliver impact across hundreds of millions of customers.