Founding AI Engineer (Application in Description)

OpenSesame; Toronto; On-site; CAD 80,000 - 100,000; Full time

Job summary

A forward-thinking company is seeking a passionate founding engineer to join their innovative team in Toronto. This role involves building an embedded AI agent that transforms how users interact with software. You'll work on cutting-edge technologies, focusing on agent orchestration, prompt optimization, and enhancing agent reliability. This is a unique opportunity to shape the future of AI agents in a fast-paced, collaborative environment. If you're excited about creating impactful solutions and thrive in dynamic settings, this position is perfect for you.

Benefits

Brand-new work laptop (Mac)

Beautiful downtown office

Strong investors and advisors

Collaborative team environment

Qualifications

• Experience building agentic workflows and LLM-integrated applications.
• Strong skills in prompt engineering for accurate outputs.
• Advanced Python skills in AI/ML system design.

Responsibilities

• Own key pieces of agent infrastructure and improve performance.
• Deploy new agent behaviors and test in production.
• Work closely with co-founders to ship fast and learn quickly.

Skills

LangChain expertise

Prompt engineering

Python

PyTorch

TensorFlow

GCP (Google Cloud)

Docker

RNNs and sequence modeling

Production-grade LLM applications

Tools

Docker

GCP (Google Cloud)

PyTorch

TensorFlow

Job description

Actual Application: https://ljc0du9aaju.typeform.com/to/R9xmAJ37

We’re looking for a passionate founding engineer to join us in person in Toronto.

At OpenSesame, we believe every product should be conversational by default. The next time someone opens a dashboard or tool, they shouldn’t feel lost; they should just be able to ask.

That’s what we’re building with Cell, our embedded AI agent.

What We’re Building

Cell can ingest any SaaS product’s APIs and turn it into a real-time, intelligent agent. We’re giving end users an AI-native way to explore, understand, and take action inside software, just by asking.

We’re starting with legacy SaaS verticals like construction tech, insurtech, logistics, and workforce management, helping them ship the Gen AI version of their products without starting from scratch.

This is a zero-to-one product. We’re building fast, shipping every week, and working directly with live customers.

What You’ll Work On

You’ll own key pieces of our agent infrastructure and be hands-on with:

• Agent orchestration and execution frameworks
• Tool selection, routing, and prompt optimization
• Improving agent reliability and performance
• Deploying new agent behaviors and testing in production
• Contributing to our agent ecosystem and technical strategy
• Working with co-founders daily to ship fast, learn fast, and push the product forward

You Should Have

• LangChain expertise: experience building agentic workflows, retrieval-augmented generation (RAG) systems, and LLM-integrated applications
• Strong prompt engineering skills, structuring prompts for context-aware, accurate outputs
• Advanced Python skills, especially in AI/ML system design and backend development
• Solid experience with PyTorch or TensorFlow for model development and deployment
• Familiarity with GCP (Google Cloud), particularly AI Platform, Cloud Functions, and ML pipeline deployments
• Working knowledge of Docker for environment management and reproducible builds
• Understanding of RNNs and sequence modeling concepts (useful in NLP/time series workflows)
• Experience building and deploying production-grade LLM applications
• Ability to document technical decisions clearly and move fast in uncertain, zero-to-one environments

Compensation Range:

$80K–$100K Salary + Equity

Bonus:

• Brand-new work laptop (Mac)
• Fully in-person in Toronto (we’re based out of a beautiful downtown office)
• Backed by strong investors and advisors, from whom you'll learn
• You’ll be working alongside a team that deeply cares about product, design, and execution

Don't Apply if:

• You want to be in a 9–5 environment
• You want to follow a hundred Jira tickets
• You don’t want an environment that is high-tempo, high-trust, and in-person

We’re looking for someone who wants to help define what AI agents become and build a real product around it.

We're not a huge fan of Resumes or GPT Essays. Send us a Loom or quick DM. Show us what you’ve built or what you’re excited about. We care way more about what you can do than what your last job title was.

Seniority level

• Mid-Senior level

Employment type

• Full-time

Job function

• Engineering and Information Technology

Industries

• Technology, Information and Internet

Referrals increase your chances of interviewing at OpenSesame by 2x

Get notified about new Artificial Intelligence Engineer jobs in Toronto, Ontario, Canada.