About Nearby AI

Nearby AI is a new company from NewsBreak building a trust-first marketplace for local home services. We help homeowners understand a problem, what it should reasonably cost, and whether to hire at all before they are connected to a provider, and we help service providers win work on fit and outcomes rather than on speed of contact.

Our mission: give people clarity and control from the first sign of a problem to a job done right, and give good contractors work they are equipped to win.

We are a small founding team. We work from evidence, keep a written record of decisions, and hold a short set of product principles we do not trade for revenue: no pay-for-rank, no sharing of customer contact information beyond what the customer approved, and no quality claims we cannot substantiate.

The role

Help build the personalized provider-recommendation pipeline end to end: user understanding with LLMs, provider retrieval and ranking, backstage agent workflows, multi-source knowledge integration, and evaluation, working with engineers and product managers from design through launch.

• User understanding and personalization: use LLMs to extract service requirements, preferences, and constraints from conversations, profiles, and context
• Provider retrieval and ranking: combine semantic search, recommendation algorithms, and provider features (capabilities, coverage, transaction-backed reputation, user fit) to improve relevance and coverage
• Agent workflows: build backstage pipelines connecting intent understanding, retrieval, provider comparison, and recommendation decisions, with explanations a user can check
• Multi-source data and knowledge integration: entity matching across business information, reviews, credentials, and service coverage
• Evaluation and delivery: build evaluation datasets, analyze failure cases and user feedback, improve quality, reliability, and latency; ship and iterate

Qualifications

Minimum:

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

Preferred:

• Embeddings, hybrid search, reranking, learning to rank, or personalized matching.
• Elasticsearch, MongoDB, PostgreSQL, vector databases, or data pipelines.
• Shipped products, open-source contributions, or independent projects showing individual impact.
• Research and personal projects count; GitHub links and demos welcome.