About this role
Build and scale core systems for Brellium’s AI-driven medical review platform, integrating modern LLMs into real-world applications and designing AI-centric systems optimized for performance and reliability. Develop evaluation pipelines and metrics to measure AI agents and workflows while owning end-to-end data pipelines and deployments.
Skills for this role
PythonTypeScriptLangChainLlamaIndexSQLRelational DatabasesAWSLarge Language Models (LLMs)ReactNext.jsData PipelinesEvaluation PipelinesAI AgentsAI Model DeploymentAI Application DevelopmentAI-Centric System DesignEnd-to-End Data Workflows