Senior Full Stack Engineer (AI Agents, Fintech)

Full time | Remote, Canada melyn is a platform built for First Nations communities across Canada. Nations use it to run housing, infrastructure, governance, finance and economic development from one system, and to secure the funding that pays for all of it. We add new Nations every week, in every province and territory.

We are not a traditional SaaS tool. We are Service-as-a-Software: we deliver outcomes, not seats. Everything we build follows OCAP (Ownership, Control, Access, Possession), the First Nations principles governing how Indigenous data is collected, stored, used and protected. OCAP is not a checkbox here. It is an architectural constraint that decides where data lives and who can touch it.

The role

Finance runs through much of the platform: funding, budgets, grants and financial records for each Nation. We also have a working AI chat assistant built on workflows and retrieval, and the next stage is an agent for every module that can act on a Nation's data, coordinate with other agents on multi step tasks, and answer any question a staff member has about their community's records.

We need someone who has built both: reliable financial systems and LLM features. These are real actions with real consequences for a government, and many of them involve financial data. OCAP means no community's data or traces can ever leave its tenant. Correctness, control and isolation matter more than raw capability. Guardrails are part of the design, not something bolted on later. You own this end to end.

What you'll do

- Build and improve the finance side of the platform: funding tracking, budgets, reconciliation and financial reporting
- Make sure every financial record is accurate and safe: clear audit trails, safe retries, numbers that always match
- Evolve the chat assistant from workflow plus retrieval into a multi agent system spanning every module, including finance
- Define how each module's agent is bounded:



tools it can call, data it can see, and hard limits on what it can do without human approval (especially anything that changes financial records)
- Build the orchestration layer for handoffs across modules, with state, retries and memory across turns
- Build the guardrails: input and output checks, prompt injection defence, PII and financial data handling
- Treat every tool call as a security boundary: least privilege, audit logs of what the agent read and did, safe handling of secrets
- Improve retrieval so answers are grounded in the Nation's own records, and the assistant says "I don't know" rather than making up a number
- Build the evaluation setup: measure false actions and unsupported answers against clear thresholds, under strict tenant isolation
- Extend the chat UI in Next.js: streaming, tool call status, approvals for risky actions, a explicit picture of what the agent did and why
- Work with the engineering lead to shape what gets built, review code, and help the team build with LLMs

Stack: Next.js on web, React Native on mobile, JavaScript and TypeScript throughout, Node.js and Python on the backend, REST APIs, PostgreSQL, AWS, models served through Amazon Bedrock.

What we're looking for

- Based in Canada and legally entitled to work in Canada
- 5+ years as a software engineer
- 2+ years building fintech or financial systems in production: payments, payouts, banking integrations, ledgers or reconciliation
- You understand what makes money code different: idempotency, audit logs, handling failed or partial transactions, and keeping data consistent




- Strong Python and TypeScript, with Node.js, PostgreSQL and React or Next.js
- Hands on with agent frameworks or your own orchestration (LangChain/LangGraph, Bedrock Agents, or similar)
- Shipped a chat based product: streaming, WebSockets or SSE, message state, making chat feel fast
- Vector databases and embeddings (pgvector, Pinecone, Weaviate, or similar), plus RAG pipelines, chunking, retrieval and reranking
- Experience extending agents with tools (structured outputs, tool schemas, permission models)
- You understand prompt injection, data leakage and tool misuse, and have built guardrails for them
- Observability, logging and tracing for AI agents
- Caching (Redis or similar) and queues or messaging (SQS, Kafka, or similar)
- Strong backend architecture instincts, and you can explain a tradeoff clearly

Strongly preferred: 1 to 2 years building with LLMs in production. It carries significant weight in our technical interview. Nice to have: Canadian payment processing through a payments API (EFT, pre-authorized debit, Interac e-Transfer), providers like Stripe or Plaid, compliance work (PCI DSS, SOC 2, or similar), multi tenant systems with strict data isolation, OWASP Top 10 for LLM applications, red teaming of LLM systems, early stage startup experience.

Why melyn

- Fully remote, flexible hours, health benefits
- Direct collaboration with leadership, no layers
- Real ownership. You define how quality works here rather than inheriting someone else's process
- Technology that makes a lasting difference for First Nations communities across Canada
- An early seat at a Service-as-a-Software company, in a category still being defined
- Small team, direct communication, light process

How we hire

Apply through LinkedIn. Our process includes an AI screening, a conversation with our team, and a technical assessment with our engineering lead.

📌 Senior Full Stack Engineer (AI Agents, Fintech) (Canada)
🏢 melyn
📍 Canada