AI Engineer
- Toronto, ON, Canada
- Greater Toronto Area, Canada, Canada
The salary range for this role is $20–$30 per hours. · Full-time
Applications open in a new tab.
Job details
- Pay
- The salary range for this role is $20–$30 per hours.
- Job type
- Full-time
- Apply by
- Posting language
- English
- Posted
Original job description
About Themis Intelligence
Themis Intelligence builds the Utility Knowledge Base (UKB) and Human-Guided Intelligence (HGI) platforms, redefining how utilities operate. Our systems transform complex operational data into clear, high-confidence decisions. We design software that empowers grid professionals to think faster, act decisively, and operate with precision in critical environments. Every product we ship is built for real-world performance: reliable, observable, and secure from day one.
We are an AI-first organization, continuously applying modern tools and workflows to improve how we plan, execute, and deliver outcomes.
About the Role
As an AI Engineer – Co-op at Themis Intelligence, you will help develop, evaluate, and improve the AI agents powering our intelligent applications and platforms. You'll work on real engineering challenges involving Large Language Models (LLMs), agentic workflows, and the reliability of AI-driven systems.
In this role, you will
- Develop, test, and improve LLM-powered agents and agentic workflows using Python and TypeScript.
- Evaluate agent performance across accuracy, factual consistency, hallucination, reasoning, and tool-use correctness.
- Experiment with prompting techniques, retrieval strategies, and model configurations to improve response quality.
- Build and maintain automated evaluation pipelines, test datasets, and reproducible benchmarks.
- Investigate agent failures, identify root causes, and implement improvements to grounding and reliability.
- Contribute to Retrieval-Augmented Generation (RAG), semantic search, and knowledge retrieval workflows.
- Analyze and visualize evaluation results to compare models, track improvements, and identify performance trade-offs.
- Collaborate through Git-based development, code reviews, and technical discussions while taking ownership of assigned deliverables.
You might thrive in this role if you
- Currently pursuing a degree in Computer Science, Engineering, Mathematics, Physics, or a related discipline.
- Strong programming skills in Python and TypeScript, with an understanding of software development fundamentals.
- Foundational knowledge of machine learning, natural language processing, or Large Language Models (LLMs).
- Experience building software or AI-related projects through coursework, research, internships, or personal initiatives.
- Familiarity with LLM APIs, prompt engineering, or AI-assisted development tools.
- Ability to debug systematically, analyze model outputs, and evaluate results critically.
- Strong problem-solving skills, willingness to learn unfamiliar technologies, and ability to work independently with guidance.
- Ability to thrive in a fast-paced, lean team environment, adapt to evolving priorities, and take initiative with minimal supervision.
Nice to Have
- Experience with agentic frameworks such as LangGraph or similar technologies.
- Familiarity with LLM benchmarks and evaluation frameworks.
- Exposure to vector databases, embeddings, semantic search, and RAG architectures.
- Experience with tool calling, structured outputs, agent orchestration, or multi-agent systems.
- Interest in AI safety, model reliability, interpretability, and real-world AI applications.
This is a 12-month duration COOP/ Intern hybrid role (four days in-office) reporting directly to the Technology Director. The salary range for this role is $20–$30 per hours. Interested candidates are invited to submit their cover letter and resume by selecting the link: https://www.fitzii.com/apply/100927?s=li
Themis Intelligence values a diverse workplace and strongly encourages women, people of all races, color, creed, ancestry, ethnic origin, sexual orientation, gender identity or expression, age, religion, national origin, citizenship status, disability, marital status, family status, and those with disabilities to apply. We use AI tools to help streamline parts of our recruitment process, but every application is reviewed by a member of our team. Themis is an equal opportunity employer. We are committed to providing accommodations for persons with disabilities. If you require accommodation, we will work with you to meet your needs. While we appreciate the interest of all applicants, only those selected for an interview will be contacted.
More about this job
Responsibilities
Develop, test, and improve LLM-powered agents and workflows, including retrieval and RAG capabilities. Evaluate model performance, build reproducible testing pipelines, investigate failures, and improve the reliability and quality of AI-driven systems.
Requirements
Applicants should be pursuing a degree in computer science, engineering, mathematics, physics, or a related field, and have strong Python and TypeScript programming skills. They should have foundational knowledge of machine learning, NLP, or LLMs, experience with software or AI projects, and the ability to debug and evaluate results critically.
Skills
- Python
- TypeScript
- Large Language Models
- Agentic Workflows
- Machine Learning
- Natural Language Processing
- Prompt Engineering
- Retrieval-Augmented Generation
- Semantic Search
- Knowledge Retrieval
- AI Evaluation
- Debugging
- Git
- Vector Databases
- Tool Calling
- Agent Orchestration
Visa sponsorship
Not detected in the job text
Categories
- Technology
- Software
- Engineering
- Data & Analytics
- Energy
Keywords
- Python
- TypeScript
- Large Language Models
- LLM-Powered Agents
- Agentic Workflows
- Machine Learning
- Natural Language Processing
- Prompt Engineering
- LLM APIs
- Retrieval-Augmented Generation
- RAG
- Semantic Search
- Knowledge Retrieval
- Automated Evaluation Pipelines
- Test Datasets
- Reproducible Benchmarks
- Hallucination Evaluation
- Factual Consistency
- Tool-Use Correctness
- Model Configuration
- Vector Databases
- Embeddings
- LangGraph
- Tool Calling
- Structured Outputs
- Agent Orchestration
- Multi-Agent Systems
- AI Safety
- Model Reliability
- Git