We are seeking a Senior AI Application/Agentic Engineer to join our Applications Delivery team. This role focuses on building practical, user-friendly solutions that integrate Large Language Models (LLMs), multi-agent systems, and other AI capabilities into web and enterprise applications. The successful candidate will develop non-deterministic AI solutions with engineering rigour, ensuring reliability, safety, and compliance within the organization’s System Development Lifecycle (SDLC) governance framework. Key Responsibilities Design, build, and maintain end-to-end AI-powered applications across frontend, backend, and AI/LLM integrations, including multi-agent orchestration patterns. Develop user-facing features such as copilots, chat interfaces, intelligent search, and workflow automation tools that incorporate LLM-driven capabilities. Build AI-powered extensions and integrations for enterprise SaaS platforms (e.g., Salesforce, Workday, ServiceNow) using their APIs and extensibility frameworks. Design and implement guardrails, output validation, and fallback mechanisms to manage the non-deterministic nature of LLM and agent-based outputs. Develop evaluation and testing strategies for non-deterministic systems, combining automated harnesses with human-in-the-loop review where traditional assertions are insufficient. Collaborate with data engineers, ML engineers, and cross-functional teams (Security, Architecture, QA, Operations) to deliver reliable AI-enabled solutions in accordance with SDLC policy. Participate in Architecture Review Board (ARB) submissions and security threat modeling when introducing new AI/LLM patterns or integration architectures. Partner with the Engineering Practice Lead to define AI-specific engineering standards, reusable frameworks, and development patterns, and evaluate new tools through the governance approval process. Required Qualifications Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field. 5+ years of experience building full stack applications with modern backend technologies. Strong programming skills in Java and/or Node.js, with working knowledge of Python. Experience integrating AI/ML services or LLMs into production applications, including API design and backend service development. Experience with cloud platforms (AWS), container orchestration (OpenShift/Kubernetes), and secrets management (HashiCorp Vault). Experience building or integrating agent harnesses for orchestrating, evaluating, and managing AI agent workflows. Demonstrated understanding of non-deterministic system behaviour, with practical experience in output validation, confidence scoring, graceful degradation, and managing variability in AI/LLM responses. Experience designing test strategies for non-deterministic outputs (e.g., evaluation harnesses, golden dataset benchmarks, semantic similarity scoring, A/B testing of prompts). Familiarity with prompt engineering techniques for controlling LLM output consistency, reducing hallucination, and implementing structured output schemas. Knowledge of secure coding practices, particularly OWASP Top Ten mitigations and AI-specific security risks such as prompt injection and data leakage. Strong problem-solving, collaboration, and software engineering skills. Preferred Qualifications Experience designing or working with multi-agent architectures, including agent orchestration, tool use, and inter-agent communication patterns. Deep familiarity with RAG architectures, embeddings, vector databases, and semantic search, with proven strategies to ground LLM outputs. Experience implementing observability for AI systems such as prompt/response logging, token usage monitoring, latency tracking, and drift detection. Knowledge of responsible AI practices such as bias detection, content filtering, and PII handling in LLM pipelines. Experience with React and Next.js or similar modern frontend frameworks. Experience extending enterprise SaaS platforms (e.g., Salesforce, Workday, ServiceNow) through their APIs, SDKs, or integration frameworks. Experience with AWS AgentCore for deploying and managing AI agents at scale. Experience working within formal SDLC governance frameworks that encompass change management, environment promotion, and CAB approvals. Track record of contributing to engineering practice development, such as authoring coding standards, building shared libraries, or mentoring teams on new technology adoption. Key Skills Full Stack Development (Java, Node.js, Python, React/Next.js, REST APIs) LLM and Multi-Agent System Design (prompt engineering, RAG, orchestration, tool use) Non-Deterministic System Engineering (output validation, guardrails, evaluation frameworks) Secure AI Development (OWASP, threat modeling, prompt injection mitigation) AI Observability and Monitoring (logging, drift detection, performance tracking) Enterprise SaaS Platform Integration (Salesforce, Workday, ServiceNow APIs) Cloud-Native and Enterprise Application Development (AWS, ROSA, CI/CD) AI Engineering Practices (standards development, governance, cross-team collaboration)