SaaS / Productivity
CamelCollect.io
A web app and browser extensions for saving LinkedIn posts into organized collections, with onboarding and subscription billing.
Read case studyAbout Dylan
Full-stack & AI engineer
I'm Dylan, a full-stack and AI engineer.
Based in Toronto, I build web products, browser extensions, and AI assistants. I've worked in IT operations, product development, and software engineering instruction.
Open to freelance projects and full-time engineering roles.
TorontoWeb productsApplied AI
Selected work
Web products, retrieval assistants, and experiments, with the implementation and my contribution in each case study.
Digital Platform / AI
Dr. Anne Hussain Platform
A book, blog, and podcast platform with an assistant that retrieves published passages and presents source citations.
Read case studyAI / Workflow Tooling
Airtable Base Doctor
An Airtable review app that checks schema and sample records, then generates interface previews, redesign proposals, and migration plans.
Read case studyAI / Social Product
TweetNet
A social simulation where configurable AI personas write posts and respond to one another in a shared feed.
Read case studyBio
How I approach the work.
I like figuring out how an application works, from the interface and API to permissions and what happens when a dependency fails.
In an existing codebase, I follow its conventions, make changes in reviewable pieces, and explain the decisions behind them. Teaching and reviewing code at General Assembly shaped how I approach debugging and technical communication.
My route here includes IT operations, philosophy, and training in acupuncture and traditional Chinese medicine. I still enjoy learning how unfamiliar systems work, whether that means tracing a bug or building an odd little experiment.
Useful over flashy
Start with what people need to do. Use AI where it helps, and simpler code where the rules are already known.
Honest technical judgment
Explain the alternatives, the costs, and the unknowns. Revisit a decision when the evidence changes.
Maintainable after launch
The people maintaining a system need to understand its code, monitor its behavior, and diagnose failures. I plan for that during the build.
Working in an existing codebase
I follow the codebase's conventions, submit changes in reviewable pieces, and explain my reasoning. Teaching and reviewing code at General Assembly helped build that habit.
Tools and experience
Tools I work with.
The choice depends on the project, the codebase, and the people who will maintain it.
Product engineering
Web applications, from the interface and database to deployment.
- Next.js and React product builds
- TypeScript-first application architecture
- Node.js and Python services
- API design, auth, billing, and admin tooling
- SaaS workflows and internal platforms
- Interface design for growing applications
AI systems
Retrieval, tool calling, and assistant interfaces, with tests for expected behavior and failure cases.
- OpenAI and Anthropic integrations
- Retrieval-augmented generation with source citations
- Vector search with pgvector and Pinecone
- Tool calling, structured outputs, and schema-constrained responses
- Context engineering and prompt routing
- Streaming assistant UX and multi-turn state management
- Evaluation suites, regression tracking, and answer quality checks
- Model routing, prompt caching, and token spend optimization
Agent orchestration
Agents that coordinate multiple steps and tools, with checkpoints for review.
- Long-running background workflows
- Scheduled and recurring automations that run unattended
- Tool-using agent loops and subagents
- Human approval steps
- Stateful execution and retries
- Multi-agent coordination patterns
- Workflow observability and failure handling
Private and local AI
Model hosting and routing choices based on data access, operating cost, and maintenance needs.
- Hermes and OpenClaw setup, custom skills, and permissions tuning
- Persistent-memory agents that keep context between sessions
- Local-model workflows with Ollama-style stacks
- Hybrid local and cloud model routing
- Model deployment and fine-tuning
- Self-hosted assistant architecture
- Secure permissions and integration design
- Slack, Discord, and internal channel integrations
Deployment and operations
Deployment, monitoring, and tests that help diagnose failures and maintain a running application.
- PostgreSQL, Redis, and data architecture
- Vercel, AWS, Docker, and deployment pipelines
- OpenTelemetry, Sentry, and structured logging
- Playwright end-to-end and integration test suites
- Monitoring, rate limiting, and incident reduction
- CI/CD and release checks
- Performance, failure recovery, and operational safeguards
- Architecture reviews for security risks
AI development workflows
AI coding tools configured for a team's repositories, tests, and review process.
- Claude Code, Codex, Cursor, and Copilot workflows
- Repository instructions and coding-agent configuration
- Long-running coding loops and agent supervisors
- AI review and validation checkpoints
- Team training and usage guidelines
- Review and testing of AI-assisted code changes
Career highlights
From IT operations to web development and teaching.
Read about my roles below, or open the resume for a summary of my experience and selected projects.
Full-stack & AI Engineer
DK Solutions
Build web products, retrieval assistants, and tools that connect to existing workflows.
- Built this site's streaming assistant with server tools, browser actions, and structured project intake
- Built Airtable Base Doctor, connecting read-only OAuth access to schema diagnostics, interface previews, and redesign reports
- Built TweetNet, a social simulation with configurable AI personas and generated posts and interactions
- Work across application code, data models, integrations, deployment, and support
AnthropicOpenAIVercel AI SDKAWSNode.jsPythonReactNext.js
Lead Developer (AI Tooling)
The Shift Weight Loss Program (Dr. Ashley White, MD)
Designed and deployed internal tools for practitioner documentation and program workflows.
- Built internal AI-assisted tools for practitioner workflows
- Worked with healthcare team members on requirements, usability, and handling sensitive information
- Delivered web tools for documentation and program management
Next.jsTypeScriptOpenAIAnthropicPostgreSQLAWS
Lead Developer
CamelCollect
Developed the web application and browser extensions for a LinkedIn content collection product.
- Built capture and collection workflows across browser extensions and the web app
- Implemented subscription billing and entitlement checks
- Handled deployment, diagnostics, support, and product changes
ReactNext.jsTypeScriptBrowser Extension APIstRPCPrismaStripe
Instructional Associate
General Assembly
Supported students learning full-stack development through code review, debugging, and project guidance.
- Reviewed student code and helped debug unfamiliar codebases
- Guided students through full-stack architecture and implementation choices
- Explained development fundamentals and maintainable coding practices
PythonReactDjangoNode.jsExpressMongoDBPostgreSQL
Web Developer
Dr. Anne Hussain
Built and maintained websites, content platforms, and publishing workflows for Dr. Anne Hussain.
- Built web applications and online learning experiences
- Developed the book, blog, and podcast platform with a retrieval assistant
- Maintained hosting and publishing workflows, including email integrations
WordPressNext.jsTypeScriptAWSPostgreSQLOpenAISupabase pgvector
IT Head
Samko and Miko Toy Warehouse
Managed IT infrastructure and developed web and reporting tools for retail operations.
- Supported the transition from in-person retail to online sales workflows
- Managed cloud and local infrastructure, security, backups, and recovery practices
- Built reporting and automation for inventory and orders
- Maintained the website backend
AWSWordPressJavaScriptPostgreSQLE-commerce Platforms
Projects and roles
Have a project or role in mind?
I welcome freelance projects and full-time engineering opportunities.
- Web products that connect an interface, APIs, data, and integrations.
- AI assistants and workflows with clear permissions and evaluation criteria.
- Teams improving an existing product through review, testing, and iteration.
Starting a conversation
For project work, we agree on scope, responsibilities, and delivery milestones before implementation.
Share the problem you want to solve or the role and team you're hiring for.