Qualifications

• 5+ years of experience in applied machine learning for information retrieval systems or NLP in production.
• Proficiency in Python and ML/NLP frameworks: LangChain, LlamaIndex, HuggingFace Transformers.
• Experience with RAG architectures and associated components such as embedding models and vector databases.
• Proficiency with LLM APIs and advanced prompt engineering techniques.
• Familiarity with RAG evaluation frameworks and building evaluation datasets.
• Experience with AWS and Databricks cloud environments.
• Demonstrated technical leadership and excellent communication skills.

Responsibilities

• Define and oversee the technical direction of retrieval pipelines.
• Establish evaluation standards for the platform and prioritize response quality.
• Define the approach to integrating LLMs in a multi-tenant context.
• Proactively identify limitations of the architecture and propose improvements.
• Mentor junior and mid-level team members in ML best practices.
• Serve as a trusted point of contact for AI-related topics for client teams and stakeholders.

Benefits

• Collaborative work environment with opportunities for professional development.
• Access to cutting-edge technologies and platforms.
• Engagement with cross-functional teams across studios and divisions.