Full Stack Engineer building AI-powered workflow automation for insurance and wealth management firms.
Developing LLM orchestration, streaming APIs, document processing, and React interfaces end-to-end.
Responsibilities
Build end-to-end AI features from backend services through to frontend UI
Design and implement LLM agent systems including tool use, planning, and multi-step execution
Develop streaming APIs (SSE) for real-time conversational interfaces
Own features from concept through production and iterate based on user feedback
Build and scale TypeScript and Python services for AI orchestration and document processing
Work with multiple LLM providers and optimize cost, latency, and quality
Develop asynchronous pipelines using AWS Lambda, SQS, S3, and Textract
Design APIs and data models connecting AI capabilities to the core platform
Build responsive, interactive React and TypeScript interfaces
Implement real-time streaming interfaces for conversational AI features
Collaborate with design on polished, accessible experiences
Contribute to frontend architecture and state management patterns
Partner with product and design to define AI feature roadmaps
Integrate with the core platform team on APIs, data models, and SDK surfaces
Contribute to architectural decisions around agent design, prompt engineering, and system reliability
Translate customer workflows into AI-powered solutions
Requirements
3–6+ years of experience building full stack applications
Strong TypeScript/JavaScript proficiency with React experience
Backend experience with Node.js/Express, Python/Django, or similar
Genuine interest in AI/LLM technology and building AI-powered products
API design experience, including streaming and event-driven patterns
AWS or cloud infrastructure familiarity
Comfort shipping iteratively in a fast-paced, high-growth startup
Strong communication and collaboration skills
Hands-on experience building with LLM APIs, tool use, prompt engineering, or agent architectures (bonus)
Document processing, OCR, or data extraction experience (bonus)
Experience with SSE, WebSockets, and real-time UIs (bonus)
Familiarity with multi-model orchestration or AI pipeline design (bonus)
High-throughput and low-latency optimization background (bonus)
Financial services or regulated-industry experience (bonus)
High-growth B2B SaaS company background (bonus)
Benefits
Competitive compensation and equity
Health, dental, and vision coverage
Unlimited PTO
Downtown Toronto office location
Office snacks and lunches
A supportive, low-ego team that values ownership and growth
Senior Applied AI Engineer building production AI agents for Tango Analytics’ real estate technology platform. Designing retrieval, evaluation, safety, and human - review capabilities for customer workflows.
Senior Applied AI Engineer building production AI agents for Tango Analytics’ real estate technology platform. Designing retrieval, evaluation, safety, and human - in - the - loop capabilities.
AI Platform Administrator configuring conversational AI, automation, integrations, and governance for ABC Fitness. Supporting software that helps fitness businesses manage clubs and engage members.
Applied AI Engineer building evaluation pipelines, production agents, and reliable clinical AI for Tali’s healthcare platform. Owning models, retrieval, routing, and observability across ambient scribe, billing, search, and clinical workflows.
Forward Deployed AI Engineer industrializing GenAI and agentic AI solutions for Keyrus Canada clients. Deploying measurable, governed AI systems across enterprise environments.
TCS Canada is hiring recent graduates for GenAI Developer roles, focusing on Generative AI, LLMs, RAG, and AI Agents. Candidates will work on real - world AI solutions in an Agile environment.
Staff AI Engineer scaling safe, evaluated agentic AI across Maple’s Canadian on - demand healthcare platform. Defining architecture, governance, observability, and cost controls for product squads.
Staff AI Engineer building and deploying enterprise AI applications for EQ Bank. Designing scalable systems, integrating LLMs, and delivering production solutions in Toronto.
Staff AI Engineer leading Calix’s enterprise agent platform for broadband providers. Building agentic workflows, RAG pipelines, integrations, and governance across product development.