Job Title: Full Stack Software Engineer
Location: Cambridge, ON | On-site
Job Type: Full-Time
Compensation: $95,000 - $115,000Benefits: RRSP, health/dental/vision package, reimbursement for tuition and professional dues, paid vacation, personal days, and sick days
The Position:Eclipse Automation is advancing a multi-year digital transformation that connects AI, engineering data, simulation, and enterprise systems to change how custom automation machines are designed, built, delivered, and supported. We are building AI services and agents "personal neurons" that give employees better access to institutional knowledge, automate complex workflows, and connect information across engineering and business systems.
We need a Full Stack Software Engineer who can learn fast, build working software, and apply modern AI capabilities both as tools in their own workflow and as features in the systems they build. This is a junior-to-intermediate role: you will work under the guidance of a Principal AI Architect and senior engineers, own implementation-sized pieces end-to-end, and grow with the platform.
Approximately 60-70% of the role will involve building AI-enabled systems (assistants, retrieval, search, integrations). The remainder is full-stack development, APIs, data pipelines, and enterprise integration that support those solutions.
What You'll Be Doing:Build AI-Enabled Systems- Implement AI assistants, chat interfaces, retrieval-augmented generation (RAG) features, intelligent search, and knowledge workflows from approved designs and specifications.
- Build tool-using and multi-step agent workflows that safely interact with enterprise APIs, databases, files, and approved business processes, with human review and failure handling.
- Implement prompt and context management, structured outputs, retrieval, embeddings, and guardrails under the direction of the Principal AI Architect.
- Help create and run evaluation workflows, automated checks and human review, for quality, groundedness, task completion, safety, and business usefulness.
- Run experiments with local LLMs and open-source models (e.g., Llama, Mistral, Qwen, Phi families) using runtimes such as Ollama or llama.cpp; measure and document results so the team can make evidence-based decisions.
- Support both locally hosted and approved cloud AI models while respecting security, privacy, and cost requirements.
Develop Full-Stack Applications and Services- Build web applications and portals used by engineers, project teams, and leadership, with a focus on interfaces that make AI capabilities understandable and usable.
- Develop React and TypeScript frontends, with a willingness to learn and grow in frontend craft.
- Build backend APIs, services, and integration components using Python (plus exposure to one of .NET/C# or Node.js).
- Implement authentication, validation, error handling, logging, and configuration required for production operation.
- Write clean, maintainable code and grow an understanding of reusable service boundaries.
Connect Enterprise Data and Systems- Build and consume REST APIs and file/event-based interfaces that connect AI solutions to internal systems and approved external services.
- Assist with data pipelines that move, transform, index, and synchronize information across engineering and business systems (PLM, ERP, MES, databases, file shares).
- Work with SQL databases (MySQL/PostgreSQL) and with vector-search or hybrid-retrieval technologies used by AI applications, with guidance on schema and performance.
- Diagnose data-quality, permissions, and integration issues and communicate blockers early.
Test, Deploy and Learn- Write testable, well-documented code with unit and integration tests; grow into end-to-end and AI-evaluation coverage.
- Use Git-based workflows, pull requests, and CI/CD through Azure DevOps or GitHub Actions.
- Deploy services to approved environments (Azure / OpenShift), monitor production behaviour, and troubleshoot failures with support from senior engineers.
- Respond constructively when testing disproves an assumption; pivot without defensiveness and preserve the learning in documentation.
Collaborate and Grow- Take direction from the Principal AI Architect and senior engineers while taking ownership of implementation details and delivery outcomes.
- Ask questions early, bring forward ideas with evidence or prototypes, and commit to agreed direction once decisions are made.
- Use AI coding tools such as Codex, Claude Code, Cursor, or similar daily, while maintaining human review, security, testing, and accountability.
- Collaborate with engineering, applications, IT, cybersecurity, and subject-matter experts to make solutions fit real workflows.
What We're Looking For:Required Experience and Capabilities- Roughly 1-4 years of software development experience (co-ops, internships, personal projects, and open-source contributions count when substantive).
- Genuine hands-on experience with AI/LLM technologies: you've built something real with them - a RAG pipeline, an agent, a chatbot, an eval harness, a fine-tune - not just prompt usage in a chat window.
- Practical experience running or experimenting with local LLMs and/or open-source models (Ollama, llama.cpp, Hugging Face), with a basic understanding of model size, context, and quality tradeoffs.
- Proficiency in Python; plus working knowledge of, or willingness to learn, .NET/C# or Node.js, and React/TypeScript.
- Working SQL skills - queries, joins, basic schema literacy; MySQL/PostgreSQL exposure is a plus.
- Experience building or consuming REST APIs.
- Comfort with Git-based workflows, code review, and writing tested code.
- Regular and effective use of AI coding assistants in your development workflow - you should be demonstrably faster and better with them.
- University degree or college diploma in computer science, software engineering, engineering, information technology, or an equivalent combination of education and relevant experience.
- Strong communication: can explain what you built, why you built it that way, and what you'd do differently.
Preferred Experience- Exposure to agent workflows, LangChain/LangGraph, LocalAI, Open WebUI, AutoGPT-style or browser-computer-use agents, or similar frameworks.
- Experience with Azure/AWS - deploying something real (even a personal project) to the cloud, cloud-based developer/agent harnesses, Azure OpenAI, or other cloud AI services.
- Vector databases, PostgreSQL/pgvector, embeddings, semantic or enterprise search.
- Open-source ecosystems and models: NVIDIA Nemotron, Llama, Mistral, Qwen, Phi; familiarity with modern agentic tooling (OpenClaw, Open Interpreter/shell agents, LM Studio).
- Manufacturing, industrial automation, engineering data, CAD/PDM, PLM, ERP, MES contexts.
- Security awareness: privacy, prompt-injection basics, access control, safe integration of AI with enterprise tools.
- GitOps/DevOps exposure, Git Actions, or ADO pipelines.
- A public GitHub, portfolio of AI projects, or hackathon results that show off the above.
What We Offer:- Mentorship from a Principal AI Architect and a team serious about practical AI, this is a rare opportunity to grow deep AI engineering skills on the job
- Reimbursement for tuition and professional dues
- 3 weeks of vacation and 3 paid personal days (to start)
- RRSP matching program
- Free snack program