Job Opportunities API

About Affinity Affinity builds relationship intelligence by processing billions of data points. The AI Platform team owns AI services powering the platform, extracting insights from structured and unstructured data. Key Responsibilities: • Build and deploy RAG pipelines combining vector search, hybrid retrieval, reranking, and contextual compression • Design multi-agent LLM systems using community frameworks and custom orchestration • Solve information extraction, storage, and retrieval problems • Collaborate cross-functionally with product, infrastructure, data engineering, and software teams Required Qualifications: • 5+ years software engineering or production ML experience • Hands-on experience with LLM applications in production, prompt engineering, and evaluation frameworks • Experience with LLM-assisted search (query understanding, text2sql, entity extraction) • Vector or graph database experience • Document chunking, embedding models, and context window optimization knowledge • Familiarity with metadata-based retrieval and reranking strategies • Model evaluation metrics experience (perplexity, hallucination rate, factual consistency) • Data security, versioning, and MLOps principles familiarity Nice-to-Have Skills: • Enterprise AI with compliance/audit/legal requirements • Dataset engineering (curation, augmentation, synthesis) • Multi-modal search experience • Graph-based recommendation systems • Agent-based AI application development • Packaging, CI/CD, and pipeline automation Tech Stack: Python-based ML pipeline with OCR for unstructured data extraction, embedding model serving, and recommendation ranking based on relevance and user preference. Benefits: Full medical/dental/vision, flexible PTO, 401(k), education budget, monthly wellness reimbursement. Salary: $160,000 - $235,000 USD (base salary, excluding equity and benefits) Hub-hybrid model: 2-3 days/week in-office for San Francisco or New York employees.