Senior AI Data Engineer

This is a fully remote position, open to applicants in Costa Rica, +3 more countries.

📋 Description

• Develop and enhance the fundamental platform for entity management and governance, focusing on entity types, attributes, cross-references (XREFs), and relationships.

• Create and refine Named Entity Recognition (NER) pipelines for text and files by integrating LLM-based models, gazetteers, pattern recognition, and blacklists.

• Expand NER functionality to accommodate new content types, including live-stream material.

• Enhance search and entity discovery through entity resolution, personalized search, filtering, and relationship navigation.

• Design and query graph-based relationship models to facilitate traversal, visualization, and connected business context.

• Implement entity-level security and access controls for data retrieval and exploration.

• Integrate new data sources and support connections with consuming applications.

• Convert business requirements into technical solutions and AI workflows, rigorously validating AI-generated code and designs.

• Collaborate with stakeholders across various business domains to define and prioritize the platform's roadmap.

• Assist with team onboarding and promote knowledge sharing.

⛳️ Requirements

• Over 7 years of software engineering experience, including the development or management of data-intensive platforms in production environments.

• Familiarity with search platforms like Elasticsearch or OpenSearch, as well as information retrieval and entity resolution.

• Understanding of graph databases and knowledge graphs, including Neo4j and Cypher.

• Practical experience in NLP and NER, encompassing LLM-based extraction and open-source models such as Gemma, Llama, GLiNER, or spaCy.

• Proficiency with PostgreSQL, Kubernetes, and observability tools like Datadog.

• Experience in data ingestion and synchronization from various source systems.

• Strong skills in systems thinking, architecture, and data modeling, with a track record in modeling complex business domains.

• Hands-on experience with AI-assisted development tools such as GitHub Copilot, Cursor, Claude, ChatGPT, and agentic workflows.

• Ability to critically assess, validate, and amend AI-generated outputs using sound engineering judgment.

• Outstanding communication skills.

• Knowledge of permission-aware data access and security filtering.

• Proficiency in at least one programming language, such as Python, Java, or another language.

🏝️ Benefits

• Equal opportunity employer dedicated to creating an inclusive workplace.