ML Engineer: Search, Recommendations & Personalization

Francisco Partners; Mountain View (CA); On-site; USD 190,000 - 300,000; Full time

Job summary

NewsBreak is seeking a Machine Learning Engineer to build intelligent systems that connect consumers with relevant local information, businesses, and services. You will work across search, recommendation, ranking, retrieval, user‑intent understanding, personalization, and marketplace matching.

This hands‑on role will take ML solutions from problem definition and experimentation through production deployment and iteration.

Qualifications

• Experience building ML, data mining, search, or related systems.
• Strong programming skills in Python, Java, or C++.
• Solid ML fundamentals, data structures, algorithms, and statistics.
• Experience with ML frameworks and production systems.
• Ability to work with large datasets and translate problems into solutions.

Responsibilities

• Build and improve ML models for search, recommendation, ranking, and matching.
• Develop systems that understand user queries, behaviors, and context.
• Apply embeddings, NLP, and LLMs to connect demand with local content.
• Design end-to-end ML pipelines from data to online serving and monitoring.
• Collaborate with product, engineering and data teams.
• Design and analyze experiments to measure impact.
• Improve relevance, engagement, conversion, retention, and marketplace efficiency.
• Explore new ML and LLM techniques and productionize them.

Skills

Machine Learning

Python

Java

C++

NLP

Embeddings

Large Language Models

Tools

PyTorch

TensorFlow

Spark

Kubernetes

Model serving platforms

Job description

NewsBreak is seeking a Machine Learning Engineer to build intelligent systems that connect consumers with relevant local information, businesses, and services. You will work across search, recommendation, ranking, retrieval, user‑intent understanding, personalization, and marketplace matching.

This hands‑on role will take ML solutions from problem definition and experimentation through production deployment and iteration.