Build and maintain production-grade AI pipelines for document ingestion, OCR, and entity extraction.
Use LLMs and retrieval-augmented techniques for accurate data classification, and apply rules and graph-based models to represent relationships between borrowers, entities, and assets.
Work with team to implement agentic in-app experience that enable users to interrogate, explore, and act on data insights.
Implement observability and feedback loops to monitor model performance, implement human-in-the-loop validation, and continuously improve accuracy over time.

Requirements

5+ years of experience (after graduation from last school/college)
1–3 years of professional experience building production-grade AI systems using large language models, agentic frameworks (e.g., LangChain, PydanticAI), and retrieval-augmented generation (RAG) pipelines
Strong proficiency in Python and applied ML frameworks such as PyTorch and Hugging Face
Experience building APIs and data pipelines with a strong foundation in system design, testing, CI/CD, and cloud deployment
Experience with prompt engineering, fine-tuning, and evaluation methods for improving real-world model performance.

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

Pythonmachine learninglarge language modelsagentic frameworksLangChainPydanticAIretrieval-augmented generationAPIsdata pipelinessystem design