Role Description You will take ownership of the search infrastructure for Ask Seeking Alpha — a financial intelligence platform powered by LLMs. Your main goal is to ensure our AI agents can find the exact financial data they need (articles, transcripts, news) in milliseconds. You will work on the Retrieval layer of our RAG architecture, combining traditional text search with modern vector search techniques. Tech Stack: - Elasticsearch (v8+) - Python (FastAPI, Asyncio) - OpenAI Embeddings - LangChain - LangSmith The Senior Search Engineer will be engaged with the company as a contractor (Private Entrepreneur). What You'll Do - Search Engine Development: Design and implement Hybrid Search strategies. You will figure out how to best combine "keyword matching" (finding specific tickers like 'AAPL') with "semantic search" (finding concepts like 'revenue growth'). - Relevance Tuning: You are responsible for the quality of search results. You will build systems to measure and improve how well the search engine answers user queries (using tools like LangSmith). - Vector Search & RAG: Manage the integration of OpenAI embeddings into Elasticsearch. You will solve challenges related to indexing long documents (e.g., earnings transcripts) so the AI retrieves only the most relevant parts. - Performance Optimization: Optimize Elasticsearch queries and index settings to ensure low latency, even for complex queries with many filters. - Python Backend: Develop and maintain the Python services that build queries and process results. We use FastAPI and Asyncio heavily. Qualifications - 5+ years of experience working with Search Engines in production. - Understanding of how indices, analyzers, and mappings work "under the hood." - Understanding the difference between Lexical Search (keywords) and Vector Search (meaning), and know when to use which. - Strong experience with Python 3.10+. - Comfortable writing asynchronous code (async/await) and building APIs. - Experience designing data schemas for search (how to structure JSON documents for efficient retrieval). Requirements - Experience building RAG (Retrieval-Augmented Generation) pipelines. - Familiarity with LangChain or similar LLM frameworks. - Experience with Evaluation tools (like LangSmith) to test search quality automatically. - Background in Finance (understanding tickers, earnings calls, etc.).

• Adopt Kotlin or Rust to develop high-performance, stable service components and client-side modules • Undertake end-to-end project delivery work, control development progress, resolve technical risks and online faults to ensure on-time and high-quality project launch • Provide technical support and technical communication for internal and external partners of the AI ecosystem • Sort out technical documents and operation specifications • Assist in sorting out technical solutions for customer business scenarios • Output technical consultation materials when needed

• Desarrollo de scripts, aplicaciones web, web services y dashboards. • Modelamiento y gestión de índices en Elasticsearch. • Desarrollo de dashboards en Kibana. • Análisis y levantamiento de requerimientos para desarrollo de proyectos. • Documentación y manuales de usuario. • Creación y edición de documentos de texto, hojas de cálculo y presentaciones.

• Work closely with the product team to codify design decisions into executable criteria • Collaboratively design and implement high-performance, low latency calculation engine code • Communicate complex technical concepts clearly and effectively to team members and stakeholders • Advocate for correctness-first approaches and foster a culture where quality is paramount