Staff AI Builder
- Toronto, ON
- Senior
- Posted 13 days ago
or apply from Claude / ChatGPT / Muse
Senior engineering role on a cross-functional team, designing and shipping agentic AI systems for enterprise clients; hybrid in Canada, production work moves in 30 to 45 days.
About the role
Enterprise workflows that need working agents rather than demos are the problem this team takes on. Reliability, security and scale matter from the first release, and the person in this seat sets the standards others build against.
At a glance
- Pay
- Not stated in the posting
- Location
- Toronto, ON
- Seniority
- Senior
- Skills
- Python, Node.js, AWS Bedrock, OpenSearch, DynamoDB, LangFuse, LangSmith, MCP
- Posted
- 3 Nov 2026
- Last checked
- 9 Nov 2026
What you will do
- Design agentic workflows: reasoning loops, tool calling, and orchestration across one or many agents
- Own RAG pipelines end to end, from chunking and embeddings to vector search in OpenSearch and refresh of stale sources
- Wire agents into AWS Bedrock and Agent Core, including MCP tool design with descriptions precise enough for correct routing
- Build evals and tracing into each agent: golden datasets, RAGAS-style metrics, LLM-as-judge, LangFuse or LangSmith
What they look for
- Deep experience making architectural calls and owning AI systems from start to finish
- Judgment to name the real trade-offs of a pattern, such as gateway centralization against latency
- Backend skill in Python and Node.js, with serverless work on Lambda and API Gateway
- Comfort designing DynamoDB single-table schemas and event-driven flows with Step Functions, SQS and EventBridge
Nice to have
- Hands-on with prompt design for production: role framing, output limits, few-shot examples
A typical week
- Write and refine system prompts, then test them against golden datasets
- Review agent failures and tune retries, fallbacks and circuit breakers
- Pair with teammates on architecture decisions and integration problems
- Ship backend services and check production health in AWS and Docker
How Keywordise applies for you
Alex Demo
[email protected]
From your CV
Yes, fully remote
- Sent
- 09:41
- Attached
- Your tailored CV
- 1Upload your CVAdd your CV once. It takes about a minute.
- 2Tailored to this jobKeywordise writes a CV and a cover letter for this job from your real experience.
- 3The form fills itselfName, email, experience and screening questions, field by field.
- 4Application sentYou get a receipt and follow it in your dashboard.
Apply with Keywordise AI7-day free trial, no card.
Apply from your AI assistant
Connect Keywordise to your assistant once, then send it the prompt. It applies for you.
Claude
- In Claude, open Settings, then Connectors, and choose Add custom connector.
- Name it Keywordise and paste the connector URL.
- Click Connect, log in to Keywordise and approve. Then send the prompt in a new chat.
https://keywordise.com/mcpDisconnect any time in your Keywordise settings.
ChatGPT
- In ChatGPT, open Settings, then Connectors. On plans that need it, turn on developer mode first.
- Add a new connector with the connector URL and choose OAuth. Leave the client ID and secret empty.
- Log in to Keywordise and approve. Then send the prompt in a new chat.
https://keywordise.com/mcpDisconnect any time in your Keywordise settings.
Muse
- Open Muse (muse.ai or the app) and send it the message below.
- If Muse asks how to sign in, answer OAuth. Open the sign-in link it sends, log in to Keywordise and approve.
- Send the prompt. Muse asks before it sends anything.
Add a custom connector called Keywordise. It is a remote MCP server at https://keywordise.com/mcp and uses OAuth. Give me the sign-in link.Muse is available in the US only for now.
Apply to Keywordise job m2enew3xtbQuestions about this job
Where is this job based?
The posting lists Staff AI Builder as a role based in Toronto, ON, Canada.
What does this job pay?
The posting does not state a salary, so there is no figure to quote.
What experience is needed?
It is a senior role. The posting asks for: deep experience making architectural calls and owning AI systems from start to finish; judgment to name the real trade-offs of a pattern, such as gateway centralization against latency; backend skill in Python and Node.js, with serverless work on Lambda and API Gateway. Skills it names include Python, Node.js, AWS Bedrock, OpenSearch.
How do I apply with Keywordise AI?
Press the Apply with Keywordise AI button and add your CV. Keywordise tailors your CV and cover letter to this posting and sends the application for you, with a free 7-day trial and no card.
More engineering jobs in Toronto, ON
- TTenstorrentSr. Engineer, Mechanical Design
- Toronto, ON
Intel CorporationCompiler Performance Engineer- Toronto, ON
- An enterprise AI governance platformStaff AI Engineer, AI Governance Platform
- Toronto, ON
- A large financial services companySenior Manager, Engineering & Build
- Toronto, ON
- C1Company 19 - John Hancock Life Insurance Company (U.S.A.)Quality Engineer
- Toronto, ON
MobSquadComputer Vision Engineer- Toronto, ON