• Instrument agents with trace-level observability (Langfuse or equivalent) • Build evaluation datasets from production traffic • Design and operate scoring pipelines (quality + robustness scoring) • Stand up and operate Braintrust or equivalent evaluation framework • Build feedback loops from eval → prompt → architecture → re-evaluation • Implement DSPy / DPO optimization as system matures • Partner with technical leadership on reliability-sensitive architecture decisions • Own dev → test → deploy → on-call sustain for your workstream

Role Description As an AI Developer (LLM & Agentic Systems), you will design and develop AI-enabled applications and intelligent systems used in client-facing projects, supporting decision-making across mining, resources, infrastructure, and environmental domains. This role can be based anywhere in Canada and plays a key part in advancing our AI-enabled platforms, internal tooling, and next-generation data solutions. - Design, build, and maintain scalable full-stack applications that integrate advanced AI and data capabilities. - Develop backend APIs and cloud-native components that support scalable data and analytics workflows. - Integrate LLMs, agentic workflows, and NLP techniques (e.g., entity recognition and entity resolution) into production-ready systems. - Contribute to the design and evolution of knowledge-based and data-driven platforms. - Develop and integrate data pipelines and knowledge-driven components (e.g., structured data, semantic layers, or knowledge graphs) into applications. - Collaborate closely with analytics, data science, knowledge engineering, and digital product teams. - Work directly with internal teams and clients to translate requirements into scalable, production-ready solutions. - Implement secure, maintainable, and testable code aligned with industry best practices. - Support CI/CD, Git workflows, and DevOps automation. Qualifications - Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related discipline. - 5+ years of professional software development experience, including 2+ years leading the design, deployment, and scaling of LLM-based or agentic AI systems in production environments. - Demonstrated experience designing end-to-end AI architectures, including data ingestion, retrieval, reasoning layers, and user-facing applications. - Strong experience with LLM workflows, including prompt engineering, evaluation strategies, agent orchestration, and tool integration. - Hands-on experience with embeddings, vector search, and RAG pipelines, including performance optimization and retrieval quality improvements. - Proven ability to design and build scalable backend systems and APIs (Python – FastAPI preferred, or Node.js), including microservices architectures. - Experience integrating structured and unstructured data into scalable AI applications. - Experience applying NLP techniques (e.g., entity extraction, entity resolution) in real-world applications. - Strong experience with cloud-native development (Azure preferred), including deployment, monitoring, and cost/performance optimization. - Experience with DevOps practices, including CI/CD pipelines, Git workflows, and multi-environment deployments (dev, UAT, production). - Nice to have: Experience with knowledge graphs and graph query languages (e.g., SPARQL, Cypher), microservices, Docker/Kubernetes, ETL pipelines, or engineering-heavy data environments. Benefits - Proudly Canadian – we are a Top 100 Employer in Canada for 2026. - A global community of brilliant minds – your next idea, mentor, or opportunity is always within reach. - Limitless opportunities start here – we help you tailor your role to match your ambition. - Flexible work, real balance – we recognize the importance of balance in our lives. Compensation - AB, BC, NT, NU, SK & YT: $93,700 – $124,200 - MB & ON: $85,500 – $117,800 - NB, NL, NS, PEI & QC: $84,700 – $112,400

• Lead complex, multi-system AI deployments end-to-end scope, architect, build, validate, and manage the customer relationship throughout. • Own the AI workshop program for your pod, customize modules per customer, lead technical sessions, translate outputs into production requirements, evolve content from field learning. • Architect multi-agent solutions selecting the right coordination pattern for each customer’s workflow characteristics and compliance requirements. • Design client-specific and industry-specific MCP resource packs that serve personalized intelligence from the server so every connected AI surface gets smarter for that customer automatically. • Own Deployment Kit quality for your pod. If a kit is not documented well enough for a solutions consultant with no engineering background to follow, it isn’t done. • Lead Solutions Enablement Sprints: transfer AI deployment patterns to solutions consultants and partners with training materials and certification criteria. • Drive the intelligence loop: author strategic memos, present field findings weekly, contribute Agent Bricks and Skills, file RFCs for platform improvements. • Mentor junior FDEs on customer engagements, code reviews, and Deployment Kit quality.

Manage the STEAM lab for small groups, engage students with relevant lessons, develop project-based learning activities, and collaborate with the Education Director to enhance curricula and activities.