Summary
✨ AI‑Generated
Join an enterprise AI engineering team as a Software Engineer Intern for a 12–14 week summer program. You will gain hands-on experience building production-scale systems that coordinate software tools, autonomous agents, and reliable multi-step workflows.
Highlights
Paid summer internship with full-time on-site engineering experience, exposure to enterprise AI systems, autonomous workflows, and production-scale software engineering.
Description
Software Engineer Intern
Company: XenonAI
Location: Minneapolis, MN (Full-Time, On-Site)
Compensation: $35 – $45 / hour (commensurate with experience)
Term: Summer 2027 (12–14 weeks)
Company Description:
XenonAI is an enterprise AI orchestration platform designed to automate complex, multi-step operations at production scale.
As organizations adopt specialized models and diverse software tools, XenonAI addresses operational fragmentation by providing a unified, high-throughput execution layer that coordinates autonomous micro-agents.
The platform connects disparate software stacks into reliable, self-optimizing pipelines, helping teams streamline critical workflows.
By combining deterministic tool execution with protocol-level context management, XenonAI reduces hallucinations and improves reliability.
Engineering and operations teams use XenonAI to transform business logic into autonomous, high-speed workflows that are built for enterprise environments.
Role Description:
The Software Engineer Intern will work full time on-site at the XenonAI office in Minneapolis, MN.
This role involves assisting in the design, development, and testing of back-end services and APIs that power the XenonAI orchestration platform.
The intern will collaborate with experienced engineers to implement features, fix bugs, write clean and maintainable code, and participate in code reviews.
Day-to-day tasks include working with distributed systems concepts, integrating services into existing architecture, writing technical documentation, and contributing to performance and reliability improvements.
The intern will also learn and apply best practices in software development, quality assurance, and DevOps workflows.
Qualifications:
Currently pursuing or recently completed a degree in Computer Science, Software Engineering, Data Science, or a related technical field.Strong foundational knowledge in Computer Science, including data structures, algorithms, and operating systems.Skills in Software Development and Programming, with experience in at least one modern programming language (e.g., Python, Java, Go, C++, or TypeScript).Understanding of Back-End Web Development concepts, such as RESTful APIs, microservices, and database interactions (SQL/NoSQL).Knowledge of Object-Oriented Programming (OOP) principles and ability to apply them in designing and implementing maintainable code.Familiarity with version control systems (e.g., Git) and collaborative development workflows.Ability to work collaboratively in a team, communicate clearly, and take feedback constructively.
Preferred Qualifications:
Hands-on experience developing with ML/AI frameworks and libraries (e.g., PyTorch, Hugging Face Transformers, vLLM, or LangChain/LlamaIndex).Familiarity with foundation model integration, prompt engineering techniques, structured model outputs, and agentic workflows (tool use, function calling, ReAct patterns).Exposure to retrieval-augmented generation (RAG) architectures, vector databases (e.g., Pinecone, Qdrant, Chroma, pgvector), and semantic search indexing.Understanding of LLM evaluation metrics, model fine-tuning (LoRA/QLoRA), context window management, or model quantization techniques (e.g., GGUF, AWQ, bitsandbytes).Experience building asynchronous, high-concurrency systems in Python (asyncio) or containerized environments (Docker).Personal projects, hackathon prototypes, academic research, or open-source contributions in the AI/ML and LLM agent ecosystem.
