Real-Time Ad ML Engineer: Low-Latency Ranking & Infra

Product Pulse; San Francisco (CA); On-site; USD 140,000 - 230,000; Full time

Job summary

Product Pulse is building the ad layer for the AI entertainment era. We seek an ML engineer to own the real‑time recommendation engine across millions of daily interactions and large annual ad spend. This full‑stack ML role spans data pipelines, model architecture, and production serving with tangible business impact.

You will design a low‑latency ranking system, build training pipelines and feature stores, and model user context for effective campaigns. In‑person SF relocation is preferred.

Qualifications

• 0–6 years of ML engineering experience. Cracked new grads welcome.
• Shipped at least one ML system in production – not just notebooks.
• Backend depth across data architecture, feature pipelines, and serving.
• Hybrid infrastructure + ML background.
• Zero‑defect mindset with latency, scalability, and reliability focus.
• Based in SF or willing to relocate quickly; in‑person preferred.

Responsibilities

• Design and ship a low-latency ad ranking system (retrieval ranking + reranking).
• Architect data pipelines and feature stores powering continuous model training.
• Build representations of user behavior from conversational data and contextual signals.
• Create a serving stack with sub‑second latency and cost efficiency.

Skills

ML engineering

Backend data pipelines

Serving infrastructure

Low latency systems

Tools

PyTorch

Spark

Docker

Job description

Product Pulse is building the ad layer for the AI entertainment era. We seek an ML engineer to own the real‑time recommendation engine across millions of daily interactions and large annual ad spend. This full‑stack ML role spans data pipelines, model architecture, and production serving with tangible business impact.

You will design a low‑latency ranking system, build training pipelines and feature stores, and model user context for effective campaigns. In‑person SF relocation is preferred.