AI Engineer - Hybrid

Purpose and Scope

The Applied AI Engineer will help design, develop, and deploy generative and agent‑based AI solutions throughout the organization. Work centers on real‑world production use cases, focusing on practical AI applications such as agentic workflows, retrieval‑augmented generation (RAG), prompt engineering, and AI‑driven automation.

The role places a strong emphasis on moving projects from experimentation to reliable, well‑governed production environments. The AI Engineer is a hands‑on, builder‑focused role and collaborates closely with software engineers, data engineers, product owners, and business stakeholders to integrate AI capabilities into operational workflows across Tolmar.

• Build and enhance AI‑powered applications and agents that support real business workflows (e.g., document analysis, task delegation, knowledge retrieval, decision support).
• Implement agentic patterns such as tool‑calling, multi‑step reasoning, and workflow orchestration in collaboration with senior engineers.
• Develop and manage prompt strategies, prompt templates, and prompt evaluation techniques for reliability and reuse.
• Implement retrieval‑augmented generation (RAG) using enterprise data sources and vector databases.

• Help transition AI solutions from prototype to production, focusing on reliability, observability, and cost awareness.
• Package AI capabilities as APIs, services, or integrations consumable by other applications.
• Contribute to CI/CD pipelines and deployment patterns for AI applications (model updates, prompt changes, configuration).
• Monitor AI solutions in production and assist with troubleshooting performance, accuracy, or usability issues.

• Work with data engineers to integrate AI solutions with governed data sources (e.g., Fabric, Dataverse, SQL).
• Collaborate with platform teams on Azure‑based AI services, Copilot integrations, and Power Platform solutions.
• Support integration of AI into existing enterprise systems (ERP, content repositories, workflow tools).

• Participate in model and solution evaluation, including accuracy, latency, cost, and usability.
• Support testing and validation activities aligned with internal AI governance standards.
• Stay current with evolving AI tools, frameworks, and best practices and contribute ideas back to the team.
• Contribute to internal documentation, reusable patterns, and AI communities of practice.
• Perform other related duties as assigned.

• Understanding of emerging standards for providing context to AI models, such as Model Context Protocol (MCP), and experience developing reusable “agent skills” to enhance model capabilities.
• Familiarity with cloud platforms (Microsoft ecosystem – Azure/Fabric) preferred.
• Strong curiosity, learning velocity, and willingness to experiment responsibly.
• Ability to communicate clearly with both technical and non‑technical partners.
• Proficiency in designing, implementing, and troubleshooting AI solutions within enterprise environments.
• Ability to analyze and interpret complex data sets, applying statistical and machine learning techniques to derive actionable insights.
• Experience with integrating AI models into business processes, workflow tools, and content management systems.
• Knowledge of data governance, privacy, and ethical considerations in AI development and deployment.
• Competency in testing, validating, and monitoring AI models for performance, reliability, and compliance.
• Skill in preparing technical documentation and creating reusable frameworks or patterns for AI projects.
• Ability to collaborate effectively with cross‑functional teams, including data engineers, platform specialists, and business stakeholders.
• Adaptability to rapidly evolving AI technologies, frameworks, and industry best practices.
• Strong problem‑solving and critical‑thinking skills, with a focus on continuous improvement and innovation.
• Demonstrated ability to manage multiple projects or tasks concurrently, prioritizing effectively to meet deadlines.