AI Engineer

Job Title: AI Engineer

Location: Cambridge, ON | On-site

Job Type: Full-Time

Compensation: $130,000 - $155,000

Benefits: RRSP, health/dental/vision package, reimbursement for tuition and professional dues, paid vacation, personal days, and sick days

Get to Know Us:

Eclipse Automation delivers cutting-edge custom automated manufacturing solutions across multiple industries. We combine advanced automation expertise with digital innovation to create smart, efficient, and sustainable manufacturing systems. Our global network includes facilities in Canada, the United States and Hungary ensuring regional expertise and global strength.

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 that give employees better access to institutional knowledge, automate complex workflows, and connect information across engineering and business systems.

We need a AI Engineer who can turn architecture and technical plans into secure, reliable, production-ready solutions. Approximately 70–80% of the role will focus on AI systems, agents, retrieval, evaluation, and model integration. The remaining work will apply full-stack development, APIs, data pipelines, and enterprise integration to support those solutions.

What You’ll Be Doing:

• Build AI Systems and Agents

  • Implement AI assistants, agents, retrieval-augmented generation systems, intelligent search, knowledge workflows, automation services, and reusable AI platform components.
  • Experimenting with local LLMs and open-source models (Llama, Mistral, Qwen, Phi) via Ollama / llama.cpp / vLLM, covering quantization, hardware sizing, and open-vs-commercial tradeoffs (cost, latency, privacy, quality).
  • Llama, Mistral, Qwen, Phi, and NVIDIA Nemotron families, with runtimes including NVIDIA NIM
  • Translate approved architecture, requirements, constraints, and acceptance criteria into working software, testable increments, deployment plans, and maintainable technical documentation.
  • Build tool-using and multi-step agent workflows that safely interact with enterprise APIs, databases, files, engineering systems, and approved business processes.
  • Implement model orchestration, prompt and context management, structured outputs, memory, retrieval, embeddings, reranking, guardrails, human review, and failure-handling patterns.
  • Create automated and human evaluation workflows for quality, groundedness, task completion, safety, latency, reliability, regression detection, and business usefulness.
  • Prototype alternatives quickly, measure results, document findings, and help the Principal AI Architect make evidence-based architecture and technology decisions.
  • Support both locally hosted and approved cloud AI models and services while respecting security, privacy, performance, capacity, 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 support AI-enabled workflows.
  • Develop responsive React and TypeScript frontends that make complex AI and engineering capabilities understandable and usable.
  • Build backend APIs, services, workers, and integration components using Python and one or more of .NET/C# or Node.js.
  • Create secure authentication, authorization, validation, error handling, logging, configuration, and administrative capabilities required for production operation.
  • Design maintainable service boundaries and interfaces that can be reused across multiple AI use cases instead of creating isolated one-off applications.

  Connect Enterprise Data and Engineering Systems

  • Build and consume REST, SOAP, GraphQL, event, and file-based interfaces that connect AI solutions to internal systems and approved external services.
  • Develop data pipelines and services that move, transform, contextualize, index, and synchronize information across CAD/PDM, PLM, ERP, MES, databases, file stores, and OpenUSD/Omniverse layers where required.
  • Work with SQL databases, including MySQL and PostgreSQL, and with vector-search or hybrid-retrieval technologies used by AI applications.
  • Protect production data and system stability while modernizing around long-lived applications, schemas, interfaces, and operational constraints.
  • Diagnose data-quality, identity, permissions, performance, and integration issues across system boundaries and communicate risks early.

  Test, Deploy and Operate

  • Write clean, testable, well-documented code with appropriate unit, integration, end-to-end, load, security, and AI-evaluation coverage.
  • Use Git-based workflows, pull requests, automated quality checks, and CI/CD through Azure DevOps, GitHub Actions, or similar platforms.
  • Containerize and deploy services to Azure OpenShift or other approved environments, monitor production behaviour, troubleshoot failures, and improve reliability based on real usage.
  • Instrument applications and AI workflows with useful logs, metrics, traces, evaluation results, usage data, and alerts while protecting sensitive information.
  • Create deployment, rollback, recovery, support, and operational documentation so systems can be maintained beyond the initial implementation.
  • Respond constructively when testing disproves an assumption; pivot the implementation without defensiveness and preserve the learning in documentation and reusable patterns.

  Collaborate and Execute

  • Work primarily from the architecture, priorities, and technical direction established by the Principal AI Architect while taking ownership of implementation details and delivery outcomes.
  • Bring forward technical alternatives and improvement ideas with evidence, prototypes, benchmarks, or clearly explained trade-offs.
  • Participate constructively in design and code reviews, incorporate feedback, and commit to the agreed technical direction once a decision is made.
  • Use AI coding tools such as Codex, Claude Code, Cursor, or similar systems as part of the daily engineering workflow while maintaining human review, security, testing, and accountability.
  • Collaborate with engineering, applications, IT, cybersecurity, operations, and subject-matter experts to ensure solutions fit real workflows and production constraints.
  Contribute to architecture records, standards, reusable libraries, playbooks, and shared knowledge that make the broader team more effective

What We’re Looking For:

• Required Experience and Capabilities

  • Five or more years building and supporting production enterprise applications, services, integrations, or data platforms.
  • demonstrated experience with — or at minimum serious hands-on experimentation with — local LLMs and open-source models.
  • Practical experience implementing AI/LLM solutions such as agents, retrieval-augmented generation, embeddings, vector search, structured outputs, tool use, evaluation, context engineering, or model integration.
  • Frontend development experience with React and TypeScript.
  • Backend development experience with Python plus .NET/C# or Node.js, including production APIs, background services, authentication, error handling, and observability.
  • Strong SQL skills, including queries, schema design, migrations, performance, and safe work with production databases; MySQL and PostgreSQL experience are valuable.
  • Experience building and consuming REST, SOAP, or GraphQL APIs and integrating systems with different data models, ownership boundaries, and operational constraints.
  • Experience with Git, pull requests, automated testing, CI/CD, containers, deployment, monitoring, and production troubleshooting.
  • Active and effective use of AI coding assistants in a professional development workflow.
  • University degree or college diploma in computer science, software engineering, engineering, information technology, or an equivalent combination of education and relevant experience.

  Preferred Experience

  • Model-serving or AI-platform infrastructure, including local or cloud inference, GPU-backed workloads, embedding and reranking services, model gateways, or capacity and performance testing.
  • NVIDIA AI stack — NIM microservices, TensorRT-LLM, Triton Inference Server, and CUDA ecosystem — for high-performance local and cloud inferenc
  • Configuring and tuning GPUs on on-prem and dedicated offsite infrastructure — driver/CUDA stack management, VRAM sizing, multi-GPU setups, power/thermal tuning, and benchmarking real-world inference throughput.
  • Developing and deploying agents and agent harnesses in the cloud — Azure (AI Foundry, AKS, Functions, managed inference), AWS (Bedrock, Lambda, ECS), or comparable GCP services, including serverless and containerized patterns.
  • Familiarity with the NVIDIA AI stack — NIM microservices, TensorRT-LLM, Triton Inference Server, and CUDA ecosystem — for high-performance local and cloud inference.
  • Agent orchestration frameworks, evaluation platforms, vector databases, PostgreSQL/pgvector, hybrid retrieval, knowledge graphs, or enterprise search.
  • Llama/Mistral/Qwen/Phi, Hugging Face tooling, quantization formats (GGUF, AWQ, GPTQ) and quality/speed tradeoffs.
  • Azure, Azure OpenShift, Kubernetes, container registries, secrets management, identity integration, infrastructure automation, and production observability.
  • Manufacturing, industrial automation, engineering data, CAD/PDM, PLM, ERP, MES, NVIDIA Omniverse, OpenUSD, simulation, or digital-twin environments.
  • Security, privacy, responsible AI, prompt-injection defence, access control, auditability, and safe integration of AI with enterprise tools and actions.

What We Offer:

• Reimbursement for tuition and professional dues
• 3 weeks of vacation and 3 paid personal days (to start)
• RRSP matching program
• Free snack program

Why Join Us:

Here at Eclipse Automation, creation and innovation are at our core, and our culture reflects that. Fast-paced and continuously fostering growth, we encourage the entrepreneurial spirit that our teams embody, and leverage each of their strengths to do better for our people, our clients, and our communities.
Our teams are made up of innovators, thinkers, and doers, with the know-how and expertise to exceed expectations, and the relentless spirit to create and reinvent. Our people are what enable us to live up to our name - to eclipse all others, inspiring and creating outcomes that change the world.

Eclipse Automation is committed to creating an accessible and inclusive work environment. It is our policy to recruit and select applicants solely on the basis of their qualifications. We are an equal opportunity employer that hires talent regardless of age, race, creed, colour, religion, national origin, ancestry, marital status, sexual orientation, gender identity or expression, disability, or any other status or condition protected by applicable law.

At Eclipse Automation, we believe in the power of human connection. We do not use AI in our hiring process; every application is personally reviewed by a member of our team to ensure each candidate receives careful consideration.

This publicly advertised job posting is for an existing vacancy. We are seeking a qualified candidate to join our team and assume the responsibilities of this role.

Eclipse Automation encourages applications from all qualified candidates. Those in need of accommodation at any stage of the recruitment process should notify [email protected]. Any information received that relates to accommodation needs of a candidate will be addressed in a confidential manner.