Staff Engineer / Ai Builder - Toronto

We’re looking for a Staff AI Builder to lead the design and delivery of AI/ML systems. This role is ideal for an experienced engineer who thrives on architectural decisions, can confidently own systems end-to-end, and contributes to technical leadership across the team.In this role, you will work as a key technical leader on a cross-functional team, defining AI architecture, leading model development and optimization, and solving challenging integration problems.You’llbe joining real, in-flight work where reliability, security, and scalability are critical.You’llestablishengineering standards, raise the bar on how we build AI systems, and contribute to the technical decisions that shape how our AI work scales over time.Why This Role Matters
At Robots & Pencils, we design AI systems fora humanworld. Our name says it all. Robots and pencilsmeansengineering paired with creativity, because every agent we shiphas towork for real people in real workflows. That balance is baked into how we operate. Every role here contributes directly to that mission. Here, you shape how AI systems integrate into enterprise operations, how teams move at real velocity, and how products create measurable impact for clients and the people they serve. We ship production-ready AI in 30 to45 days. That pace demands people who take ownership, lead with craft, and care deeply about what they put their name on.What You’ll Do
Agentic & GenAI Engineering
Design and build agentic workflows
— reasoning loops, tool/function calling, and orchestration across single- and multi-agent architectures — with clear judgment on which pattern fits the problem and which doesn’tBuild and maintain RAG pipelines
: chunking strategy, embeddings, vector search (OpenSearch), re-ranking, and staleness/refresh handling for dynamic knowledge sourcesIntegrate with AWS Bedrock and Agent Core
, including MCP-based tool design — writing tool descriptions precise enough that an orchestrator routes correctly every timeWrite and iterate on production system prompts
— structured role framing, output constraints, and few-shot design — not just prompt tinkeringBuild eval and observability into every agent you ship
: golden datasets, RAGAS-style metrics, LLM-as-judge (as both a runtime guardrail and an offline eval), and tracing via LangFuse/LangSmith or equivalentDesign for LLM failure, not just LLM success
: retries with backoff and jitter, circuit breakers, fallback models, and a clear user-facing story when something upstream degradesFull-Stack & Platform Engineering
Build backend services in Python and Node.Js, including serverless architectures (AWS Lambda, API Gateway) that support agentic workflowsDesign DynamoDB single-table schemas — composite keys, transactional writes — for conversation state, agent memory, and session historySupport event-driven orchestration (Step Functions, SQS, EventBridge) for asynchronous agent operations, with an eye toward reliability and clean error handlingContribute to frontend integration points so agentic features land cleanly for end users, and write clean, well-tested code across the stackSupport deployment, monitoring, and production troubleshooting in cloud-native environments (AWS, Docker), with guidance from senior engineers where neededCollaboration & Technical Leadership
Bring informed technical judgment to architecture discussions — naming the real trade-offs of a pattern (e.G., gateway centralization vs. latency, single- vs multi-agent design) rather than defaulting to what’s familiarPartner with product, design, and delivery leads across global teams to scope and ship features end-to-endMentor other engineers on the pod and help raise the bar on agentic engineering practices, including AI-assisted development tools like Claude CodeOwn assigned features and releases end-to-end — including the unglamorous parts: debugging, hardening, and keeping production systems trustworthyWhat You’ll Bring
6+ years of professional software engineering experience, including meaningful time shipping GenAI/LLM-powered systems in production — not just prototypesReal, hands-on depth in
agentic AI
: reasoning loops, tool/function calling, multi-agent orchestration, and a considered point of view on when single-agent design beats multi-agent, and whyPractical
RAG expertise
: chunking strategies, embeddings, vector databases (OpenSearch or similar), cosine similarity search, and re-ranking — you can explain the mechanism, not just the terminologyExperience building
evaluation and observability
for LLM systems: golden datasets, LLM-as-judge, RAGAS or comparable metrics, and tracing tools like LangFuse/LangSmithStrong
prompt engineering
skills — you can write a production system prompt with real structure and constraints on request, not just describe the conceptHands-on experience with the
AWS GenAI stack
: Bedrock, Agent Core, Lambda, DynamoDB (single-table design), S3, SQS, EventBridge, Step FunctionsStrong Python and Node.Js skills, with experience building full-stack applications and RESTful APIsSolid understanding of production reliability patterns for LLM-backed systems: retries/backoff, circuit breakers, fallback models — as a bundle, not a single tacticExperience with containerization (Docker) and cloud-native deploymentComfort owning ambiguous, integration-heavy problems, and the ability to go a level deeper when someone pushes on your answer instead of staying abstractLegally authorized to work in Canada and
eligible to secure immediate U.S. non-immigrant work authorization (e.G., TN status under USMCA)
for mandatory weekly on-site client delivery (3 days/week) in the United States.Helpful Extras and Unique Skills
Direct experience with Amazon Bedrock Agent Core — agent registration, MCP tool wiring, memory/session management, gateway provisioningExperience in a regulated or high-stakes domain (education, healthcare, financial services) where evaluation rigor and reliability carry real consequencesFamiliarity with workflow orchestration tools such as Step Functions, Sequencer, or similar state-machine-based systemsA point of view on LLM observability tooling, gained from actually running it in production rather than reading about it_The below range reflects the range of possible compensation for this role at the time of this posting. We may ultimately pay more or less than the posted range. This range may be modified in the future. An employee’s position within the salary range will be based on several factors including, but not limited to, relevant education, qualifications, certifications, experience, skills, seniority, geographic location, performance, shift, travel requirements, sales or revenue-based metrics, any collective bargaining agreements, and business or organizational needs. The salary range for this role is $ $165,604 - $228,491 USD.We offer a comprehensive package of benefits including paid time off, medical/dental/visioninsuranceand 401(k) to eligible employees.An offer of employment may be conditional upon successful completion of a background checkin accordance withlocal legislation and ourcandidateprivacy notice. Your current employer will not be contacted without your permission. We are committed to ensuring equal employment opportunities for all job applicants and employees. Employment decisions are based upon job-related reasons regardless of an applicant’s race, color, religion, sex, sexual orientation, gender identity, age, national origin, disability, marital status, genetic information, protected veteran status, or any other status protected by law.
#J-18808-Ljbffr