AI Engineering Intern 🎓

The AI Engineering Intern will support the next phase of Bio-Techne’s GenAI transformation by designing components for multi-agent systems, multi-component prompting, model context protocol, evaluator agents, and large-scale retrieval pipelines. This role focuses on long-term platform capabilities that strengthen our enterprise AI infrastructure.

Key Responsibilities:

• Design and implement components for production multi-agent architectures, including supervisor patterns, parallel execution graphs, tool orchestration, and state persistence strategies

• Develop multi-component prompting systems (MCPS) with dynamic prompt assembly, context injection, and modular template management for enterprise-scale applications

• Build evaluator agents that leverage LLM-as-judge patterns, automated regression testing, and continuous monitoring for deployed AI systems

• Architect retrieval pipelines integrating hybrid search, reranking models, chunking optimization, and metadata filtering across large heterogeneous document corpora

• Contribute to active learning workflows with stakeholders across the company where production feedback loops continuously improve GenAI model performance over time

• Support MLOps infrastructure, including model versioning, data storage integration, and scalable serving patterns on Databricks

• Prototype emerging capabilities such as agentic tool use, memory systems, and autonomous workflow execution to inform platform roadmap decisions

Program Requirements:

• Must be a currently enrolled student pursuing a graduate-level degree in a field relevant to the internship

• Must be able to work full-time during the duration of the internship program

Experience Qualifications:

• Currently pursuing a MS degree in Computer Science, Machine Learning, Data Science, or a related field with coursework in NLP, deep learning, or distributed systems.

• Hands-on experience building applications with LLM frameworks such as LangChain, LangGraph, Llama Index, or similar orchestration tools.

• Proficiency in Python with experience writing production-quality, modular code.

• Familiarity with vector databases, embedding models, and retrieval-augmented generation patterns.

• Experience with cloud platforms (Databricks, AWS, Azure, or GCP) and MLOps concepts such as model versioning and deployment pipelines.

• Strong problem-solving skills with the ability to translate ambiguous requirements into working prototypes.

• Excellent written and verbal communication skills for documenting technical work and collaborating across teams.