Intern Research Engineer - AI Agent Systems
$58,000–$104,000 year
On-siteMarkham, Ontario, Canada
Job Summary
Architect and implement high-scalability AI Agent pipelines, transforming complex requirements into reliable execution structures using TaskGraph IRs and multi-agent coordination frameworks. Develop and optimize automated code generation, reasoning, and self-debugging loops that interact directly with multi-framework environments. Design advanced memory substrates for Agents to address long-context handling and state persistence challenges. Establish rigorous, automated evaluation frameworks to benchmark Agent execution accuracy and latency under non-deterministic LLM behaviors. Translate cutting-edge research in Agentic workflows into production-grade, highly performant software libraries. This internship targets candidates pursuing a Master's or Bachelor's in Computer Science with proficiency in Python, TypeScript, and frameworks like LangGraph or AutoGen. The total target annual compensation ranges from $58,000 to $104,000.
Required Qualifications
- Currently pursuing a Master's or Bachelor's Degree in Computer Science or a highly quantitative field, with a focus on AI, Software Engineering Systems, or Distributed Systems
- Proficient in orchestrating LLMs programmatically
- Deep understanding of Agentic design patterns (Planning, Memory, Tool Use, Multi-Agent Collaboration)
- Exceptional coding skills in Python and/or TypeScript/Node.js
- Familiarity with structural design patterns and engineering clean, maintainable codebases
- Deep experience with frameworks such as LangChain, LlamaIndex, LangGraph, CrewAI, AutoGen, or building custom agentic runtime systems
- Ability to quickly digest, implement, and improve upon cutting-edge ArXiv papers on LLM reasoning and code generation
Desired Qualifications
- Contributions to open-source AI Agent frameworks, developer tools, or compiler-related projects
- Experience with Code-LLM optimization (e.g., custom fine-tuning for code generation, structured outputs), embedded database engines or high-performance vector stores
- Familiarity with cross-framework mobile compilation or bridge layers (e.g., Android/AOSP or hybrid application runtimes)
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.