Applied AI/ML Intern

Role Overview

Join Banyan Intelligence's core engineering group to help build the next generation of applied AI systems and agentic workflows. As an Applied AI/ML Intern, you will work closely with our research and product teams to prototype intelligent agents, build evaluation harnesses, optimize model performance, and design infrastructure that supports reliable AI behavior across diverse environments. You will get hands-on experience with modern LLM technologies, retrieval-augmented generation (RAG), multi-modal AI workflows, and full-stack engineering for AI-powered systems.

Responsibilities

• Build and maintain datasets, evaluation harnesses, and testing pipelines for LLM-based agents
• Prototype AI workflows, RAG pipelines, tool-calling agents, and reasoning chains
• Develop Python- and TypeScript-based services that integrate AI inference with backend APIs
• Implement front-end components in ReactJS to support agent dashboards, monitoring, and internal tools
• Containerize services and pipelines using Docker; automate deployments on Linux-based systems
• Assist in performing agent benchmarking, measuring hallucination rates, and improving reliability
• Collaborate with senior engineers to encode operator constraints, safety logic, and domain-specific playbooks
• Document experiments, model behaviors, and design insights for internal research notes
• Contribute ideas to improve model prompting strategies, evaluation flows, and system robustness

Qualifications

• Pursuing a Bachelor's or Master's degree in CS, AI/ML, ECE, or a related technical field
• Strong programming skills in Python and TypeScript
• Experience building UIs or tools using ReactJS
• Understanding of REST APIs, backend development, and integration workflows
• Familiarity with LLMs, prompt engineering, embeddings, or basic RAG concepts
• Comfortable working with Linux systems and Docker for development workflows
• Ability to break down ambiguous problems and execute independently
• Clear written communication and documentation skills

Nice to Have

• Experience with LangChain, LlamaIndex, or orchestration frameworks
• Exposure to LLM inference servers such as Ollama, vLLM, llama.cpp, or cloud-hosted endpoints
• Background in information retrieval, vector databases, or search systems
• Knowledge of ML model serving, optimization, or fine-tuning workflows
• Familiarity with DevOps tools, observability, or experiment-tracking frameworks
• Previous internship experience in AI/ML, backend, or full-stack engineering