Role Description VAS is seeking an AI Engineer to lead building of scalable real-time production grade applications that use AI/ML models. This is a strategic, hands-on position for an experienced technical leader who has a track record of shipping AI-enhanced customer applications and tooling used by engineering teams. This role will be focused on embedding LLMs, agent-based systems, and automation into core development workflows—boosting productivity, reducing manual toil, and accelerating delivery, essentially transforming how our engineers build, test, and ship software. Responsibilities - Understand customer challenges and how integrating AI capabilities can help lead to solutions that have AI as a differentiator. - Identify opportunities to apply AI for efficiency, growth, and customer value. - Drive awareness of AI capabilities and demonstrate how it can address customer needs, improve efficiency, reduce costs, and drive growth. - Drive transformation from AI-Ad Hoc to AI-Native engineering practices. - Serve as the AI technical SME, conduct R&D (research and development) to meet the needs of our AI strategy. - Continuously assess emerging AI tools and make data-driven recommendations. - Measure & Accelerate Adoption: Establish KPIs, track progress from the current to 100% adoption, implement interventions to accelerate uptake and communicate impact. - Build Center of Excellence: Create forums for knowledge sharing, celebrate wins, and foster peer-to-peer learning. - Establish AI governance frameworks and guardrails covering compliance, security, privacy, and ethical AI practices, and embed them into development workflows. LLM Agents & Prompt Engineering - Architect and implement LLM agents. - Build composable, tool-augmented reasoning chains (e.g., RAG, CoT, ReAct, planner-executor). - Integrate vector databases and knowledge graphs to support retrieval-augmented generation (RAG). - Design and maintain high-quality prompt strategies for robustness and reliability. Model Context Protocol (MCP) & Backend - Develop and maintain scalable APIs, supporting synchronous and asynchronous agent execution. - Integrate Model Context Protocol (MCP) to enable secure and structured access to external data and tools within agent workflows. - Implement state tracking, context-aware input dispatch, and modular plugin integration within the control plane. Evaluation, Testing & Observability - Build unit and behavioral tests for agents, tools, and workflows. - Develop tooling for trace analysis, agent state debugging, and hallucination tracking. - Compare and benchmark agent orchestration frameworks for trade-offs in speed, reliability, and usability. Model Fine-Tuning & MLOps - Integrate, deploy, fine tune and monitor models in production using cloud providers. - Set up agent logging, observability dashboards, and recovery workflows. Front-end & User Experience - Collaborate with front-end developers or build user-facing components using React, TypeScript. - Ensure seamless user and agent interaction via UI and API bridges. Qualifications - Bachelor of Science in Software Engineering, Computer Science, Data Science, AI/ML or related field preferred. - 10+ years of experience in software development and design. - Proven experience in AI/ML solution design and hands-on experience with AI-powered development tools. 3+ years of experience preferred. - Strong knowledge of Large Language Models, Generative AI, NLP, and Machine Learning concepts. (3+ years of experience preferred). - Hands-on experience with deep learning frameworks. - Experience with RAG pipelines, vector databases, and agentic frameworks. - Familiarity with cloud-based AI services. Company Description For the past 40 years we’ve woken up each day to support those that never stop feeding the world – and we have no plans to quit. We set the standard for farm management solutions and fix our eyes on raising the bar to meet the next generation of expectations. - Our software and information solutions help collect and connect a farm's data – from herd management to feed performance, tracking and more. - These insights are a source of truth, empowering producers and their trusted advisors to make profit-driven and sustainable management decisions. - Whether near or far, large or small, VAS is at the heart of your dairy. - VAS has deep roots in the industry through its origin within the URUS family of companies. - As a holding company with cooperative and private ownership, URUS is a family of businesses at the heart of the dairy and beef industry – Alta Genetics, GENEX, Genetics Australia, Leachman Cattle, Jetstream, PEAK, SCCL, Trans Ova Genetics and VAS. - Each organization has its unique identity, products, and services. - These companies work globally to provide cutting-edge dairy and beef genetics, customized reproductive services to maximize conceptions, dairy management information to take producers to the frontline of progressive dairy farming, and an array of products and services to help bovines reach their full genetic potential. - URUS has 9 brands in 17 retail countries and employs nearly 2,800 people globally.

• Owns the development and governance of Mercy’s enterprise AI architecture • Defines and maintains enterprise-wide AI architecture blueprints and standards • Defines standards and reference architectures for the development and safe deployment of agentic AI systems • Leads the identification of capabilities, outcomes, and success criteria for AI solutions • Guides the selection of AI model solutions in partnership with the AI engineering team • Leads the development of training and testing plans and evaluates AI solutions • Engages with external AI solution providers to evaluate and recommend innovations

• Lead synchronous remote lectures and "build-along" sessions • Guide students through hands-on exercises including agent design patterns and API integration • Provide real-time troubleshooting and debugging support in Python • Break down complex systems-thinking into actionable steps • Hold dedicated sessions for student feedback and guidance

• 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