AI Engineer Intern

United States Digital Space LLC; Toronto; On-site; CAD 27,552 - 41,328; Part time

Benefits offered by this job

Hybrid work model in Toronto

Downtown Toronto office

Growth & Learning opportunities

Job summary

United States Digital Space LLC is seeking an AI Engineer Intern to build production-ready AI agents and applications. You will contribute to Continuum while developing agentic solutions for enterprise use cases, collaborating across model orchestration, memory systems, and tools.

You will work with OpenAI, Anthropic, Gemini and other models, focusing on robust routing, memory, and safe, scalable deployments in a hybrid Toronto setting.

Qualifications

• Pursuing or recently completed CS/AI/data science or related degree.
• Strong Python programming skills.
• Solid understanding of ML, NLP and LLM fundamentals.
• Experience building an LLM-powered or agentic application.
• Familiarity with prompt engineering, embeddings, RAG, tool calling.
• Experience with APIs, Git, databases, and software engineering practices.
• Ability to research problems and communicate results clearly.
• Interest in building reliable AI systems beyond demos.

Responsibilities

• Build and improve agent orchestration and multi-agent workflows.
• Develop agentic applications for enterprise use cases using Continuum.
• Work with different commercial and open-source models (OpenAI, Anthropic, Gemini, Llama, Qwen, Mistral, etc.).
• Improve intelligent model routing based on task complexity, quality, latency, and cost.
• Build persistent memory and state-management for long-running agent workflows.
• Develop tool-calling functionality and integrations with APIs, databases, and enterprise systems.
• Connect agents with external services using MCP servers and function tools.
• Design context-engineering and retrieval pipelines using vector/graph databases.
• Implement AI guardrails for safety, security, access control, and data privacy.
• Create evaluation pipelines to measure accuracy, groundedness, hallucination, tool usage, latency, and cost.
• Improve observability and traceability of agent decisions and workflow execution.
• Optimize prompts, model usage, token consumption, and infrastructure costs.
• Build APIs, backend services, and user-facing prototypes for agentic apps.
• Write clean, reusable, well-tested, documented Python code.
• Contribute to Continuum’s open-source codebase and docs.

Skills

Python

Machine learning

NLP

LLM fundamentals

APIs

Git

Education

Bachelor's degree in Computer Science / AI / Data Science / Software Engineering or related field

Tools

LangChain

LangGraph

LlamaIndex

Open-source models

Job description

About the company

At the company, we live and breathe data. Since 2020, we’ve been helping Fortune 500 companies unlock growth through innovative digital solutions that drive real business impact. With teams across Canada, the U.S., and India, we’re growing quickly and looking for curious, motivated individuals who are excited to learn, build, and solve meaningful problems with technology.

About Continuum

Continuum is an enterprise AI agent execution and control platform designed to help teams build, run, and deploy reliable agentic applications. It provides agent orchestration, multi-model routing, persistent memory, tool integration, durable workflows, governance, guardrails, evaluation, and observability.

We are looking for an AI Engineer Intern interested in building production‑ready AI agents and applications. You will contribute to the Continuum platform while also using it to build agentic applications for real enterprise use cases.

This is a hands‑on engineering role. You will work across agent orchestration, memory systems, model optimization, retrieval, tools, guardrails, evaluation, and application development.

What You’ll Be Doing

• Build and improve agent orchestration and multi‑agent workflows.
• Develop agentic applications for enterprise use cases using Continuum.
• Work with different commercial and open‑source models, including OpenAI, Anthropic, Gemini, Llama, Qwen, Mistral, and others.
• Improve intelligent model routing based on task complexity, quality, latency, and cost.
• Build persistent memory and state‑management capabilities for long‑running agent workflows.
• Develop tool‑calling functionality and integrations with APIs, databases, and enterprise systems.
• Work with MCP servers and function tools to connect agents with external services.
• Design context‑engineering and retrieval pipelines using vector and graph databases.
• Implement AI guardrails for safety, security, access control, data privacy, and policy enforcement.
• Create evaluation pipelines to measure accuracy, groundedness, hallucination, tool usage, workflow completion, latency, and cost.
• Improve the observability and traceability of agent decisions, tool calls, and workflow execution.
• Optimize prompts, model usage, token consumption, response time, and infrastructure costs.
• Build APIs, backend services, and user‑facing prototypes for agentic applications.
• Write clean, reusable, well‑tested, and documented Python code.
• Contribute to Continuum’s open‑source codebase, examples, documentation, and developer experience.

What We Are Looking For

• Currently pursuing or recently completed a degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related field.
• Strong programming skills in Python.
• Good understanding of machine learning, natural language processing, and LLM fundamentals.
• Experience building at least one LLM‑powered or agentic application.
• Familiarity with prompt engineering, embeddings, RAG, tool calling, and structured outputs.
• Experience working with APIs, Git, databases, and standard software engineering practices.
• Ability to research complex technical problems, experiment with different approaches, and clearly communicate results.
• Strong interest in building reliable AI systems, not just basic LLM demos.

Nice to Have

• Experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI, or similar technologies.
• Familiarity with OpenAI, Anthropic, Gemini, AWS Bedrock, or open‑source models.
• Experience with vector databases such as Milvus, Pinecone, Weaviate, or Chroma.
• Experience with graph databases such as Neo4j.
• Knowledge of PostgreSQL, Redis, Docker, Kubernetes, or cloud infrastructure.
• Familiarity with AI observability and evaluation tools such as Langfuse.
• Understanding of multi‑tenancy, identity management, authorization, or enterprise security.
• Experience with model routing, inference optimization, prompt compression, or cost optimization.
• Contributions to open‑source AI projects, research, hackathons, or technically strong personal projects.

Hourly Pay

• $20 - $30/Hr (CAD)

Why You’ll Love Working at the company

At the company, your work matters. We’re a growing data product company making a big impact with Fortune 500 clients and as we scale, you’ll have the chance to shape solutions, influence strategy, and grow your career alongside us.

Here’s what you can expect when you join our team:

• Hybrid Flexibility: Enjoy a hybrid model with three days per week in our Toronto office.

• Downtown Toronto Office: Work in the heart of the city.

• Growth & Learning: Access extensive learning and development resources to keep leveling up your skills.

Inclusion at the company

*the company is an equal‑opportunity employer committed to creating a safe, diverse, and inclusive environment. We encourage applicants of all backgrounds including ethnicity, religion, disability status, gender identity, sexual orientation, family status, age, and nationality to apply. If you require accommodation during the interview process, let us know and we’ll be happy to support you.*