Support the design, development, and deployment of agentic AI systems operating in secure, air-gapped, and edge environments. Work alongside senior engineers to build and test LLM-based pipelines, contribute to agentic workflow development, and assist with model optimization for constrained and offline deployment targets. Gain hands-on experience with real production-oriented AI systems at the intersection of machine learning, systems engineering, and infrastructure-aware deployment. 

Responsibilities 

• Contribute to the design and implementation of agentic AI workflows, including multi-agent orchestration, tool use, and reasoning loops 
• Assist with the deployment of LLM-based systems in air-gapped, on-premises, and edge environments under the guidance of senior engineers 
• Support the build-out of secure inference pipelines designed to operate without external network access 
• Write clean, modular code that integrates ML components into broader software systems and pipelines 
• Run and test models on edge hardware platforms and constrained compute targets; assist with performance and memory optimization 
• Support model fine-tuning and distillation experiments, including data preparation, training runs, and evaluation 
• Contribute to reproducible engineering workflows, including version control, containerization, and structured testing 
• Author and maintain documentation pertaining to deployment processes, system configurations, and experiment results 
• Troubleshoot issues across the stack, from model behavior through API layer through infrastructure, and report findings clearly 
• Assist with hardware configuration tasks for GPU workstations and servers as needed, with guidance provided 
• Engage with senior engineers to understand system changes, contribute to evaluations, and provide feedback for continuous improvement 

• Must currently be pursuing a Bachelor’s degree in Computer Science, Computer Engineering, Software Engineering, or a related technical discipline 
• Strong Python programming skills 
• Understanding of basic software engineering principles – code modularity, debugging, and testing 
• Understanding of machine learning fundamentals and neural network basics 
• Familiarity with Git and modern software development workflows 
• Familiarity with REST APIs and basic software integration concepts 
• Ability to work independently, prioritize tasks, and document work clearly 
• Effective written and verbal communication skills 

Preferred Qualifications

• Experience with LLM inference or serving frameworks such as vLLM, Ollama, llama.cpp, or Hugging Face Transformers 
• Any hands-on experience with model fine-tuning or distillation, including course projects or personal experiments
• Familiarity with agentic frameworks such as LangChain, LangGraph, AutoGen, or similar 
• Experience deploying or running software in constrained, offline, or non-cloud environments 
• Exposure to containerization tools such as Docker 
• Any familiarity with GPU setup or configuration for ML workloads; curiosity about hardware is welcome, deep expertise is not expected 
• Interest in or exposure to edge hardware platforms such as NVIDIA Jetson, Raspberry Pi, or similar devices