Generative AI Engineer Intern

Symple Lending•Tampa, FL

2d•Hybrid

About The Position

We’re looking for a Generative AI Engineer Intern to join our Data & AI team in a hands-on, high-impact internship role working directly on real production AI systems. This is an unpaid internship opportunity designed for students or recent graduates who want practical experience building and improving enterprise-grade AI applications in a live financial services environment. In this role, you’ll work alongside our Data Scientist to support and enhance Syble, Symple Lending’s AI-powered compliance platform that processes over 1,000 customer call transcripts per day. You’ll gain direct exposure to LLM engineering, prompt optimization, RAG pipelines, AWS infrastructure, and production AI workflows while contributing to systems used by sales leadership and executive teams. If you enjoy building with AI, experimenting with new technologies, and solving real-world problems with data and automation, this role is for you.

Requirements

Currently pursuing or recently completed a Bachelor’s or Master’s degree in Computer Science, Data Science, Information Systems, or a related field
Strong Python programming skills
Basic understanding of LLM concepts, prompts, RAG, and hallucination challenges
Familiarity with SQL and data querying
Curious, self-motivated, and eager to learn in a fast-paced environment

Nice To Haves

Experience with LangChain, LlamaIndex, or similar LLM orchestration frameworks
Exposure to vector databases such as ChromaDB, Pinecone, or FAISS
Familiarity with AWS services including S3, Lambda, or EC2
Experience working with OpenAI, Anthropic, or similar LLM APIs
GitHub portfolio or personal AI/ML projects
Experience with Jupyter notebooks and data exploration workflows
Exposure to NLP concepts, including embeddings and semantic similarity
Familiarity with pandas, NumPy, or machine learning workflows
Coursework or self-study in machine learning or deep learning

Responsibilities

Write, test, and optimize prompts for our AI-powered compliance grading systems
Build evaluation datasets and testing frameworks to measure model performance
Assist in improving Retrieval-Augmented Generation (RAG) pipelines using ChromaDB and Amazon S3
Experiment with chunking strategies, embedding models, and retrieval tuning
Research and prototype new LLM frameworks, embeddings, and agentic AI workflows
Write SQL queries against Amazon Redshift to analyze transcript and operational data
Validate model outputs and support analytical workflows across sales and loan origination operations
Use Python and Jupyter notebooks to explore data and build internal tooling
Support testing and QA for existing AI pipelines and production grading systems
Identify edge cases, inconsistencies, and opportunities for system improvements
Document prompt versions, pipeline logic, and model configurations to support scalability and maintainability