AI Intern: LLM-Powered Personalization & Retrieval

Francisco Partners; Mountain View (CA); On-site; USD 60,000 - 140,000; Full time

Job summary

NewsBreak’s Nearby AI team is seeking a candidate to help build the personalized provider-recommendation pipeline end to end: user understanding with LLMs, provider retrieval and ranking, backstage agent workflows, and cross‑source knowledge integration.

You’ll collaborate with engineers and product managers to ship these features, applying embeddings, search and ML concepts, with emphasis on quality, latency, and meaningful user outcomes in a fast-growing startup environment.

Qualifications

• Pursuing a bachelor's degree or higher in Computer Science, AI, or related field.
• Proficient in Python or Java with solid data structures and algorithms.
• Hands-on experience developing LLM applications or agents (RAG, workflows, evaluation harnesses).
• Understanding of search, recommendation, or ML fundamentals.
• Strong problem-solving and communication; initiative to own results.

Responsibilities

• User understanding and personalization using LLMs to extract requirements.
• Provider retrieval and ranking using semantic search and recommendations.
• Build backstage agent workflows and explanations for users.
• Integrate multi-source data for matching providers.
• Create evaluation datasets and improve quality, latency, and reliability.

Skills

Python/Java

LLM applications

Search & recommender

Problem solving

Communication

Education

Bachelor's degree or higher in CS/AI

Tools

Elasticsearch

MongoDB

PostgreSQL

Vector databases

Data pipelines

Job description

NewsBreak’s Nearby AI team is seeking a candidate to help build the personalized provider-recommendation pipeline end to end: user understanding with LLMs, provider retrieval and ranking, backstage agent workflows, and cross‑source knowledge integration.

You’ll collaborate with engineers and product managers to ship these features, applying embeddings, search and ML concepts, with emphasis on quality, latency, and meaningful user outcomes in a fast-growing startup environment.