Qualifications

• 5+ years of applied machine learning experience in information retrieval systems or NLP in production.
• Proficiency in Python and relevant ML/NLP frameworks including LangChain and HuggingFace Transformers.
• Experience with RAG architectures and embedding models such as OpenAI and Cohere.
• Proficiency in LLM APIs like Claude and techniques for prompt engineering.
• Familiarity with RAG evaluation frameworks and metrics like MRR/NDCG.
• Experience with AWS and Databricks environments, including MLflow and Feature Store.
• Demonstrated leadership ability and strong communication skills.

Responsibilities

• Define and oversee the technical direction of retrieval pipelines including chunking and semantic indexing.
• Establish evaluation standards to prioritize response quality in the development cycle.
• Define integration strategy for LLMs in a multi-tenant context, focusing on cost control and context management.
• Identify architectural limitations proactively and propose enhancements before users are affected.
• Mentor junior and mid-level team members on machine learning best practices.
• Serve as a trusted point of contact on AI-related topics for client teams and stakeholders.