Overview The AI Engineer V (Principal) is the most senior individual-contributor technical authority for artificial intelligence and machine learning within Assist Rx Engineering. Reporting to the Vice President, Engineering, this role defines and drives the company’s AI technical strategy and leads the design, build, and deployment of production-grade AI solutions across the specialty medication access ecosystem, including large language model applications, predictive models, intelligent document processing, and agentic automation that improve speed, accuracy, and scale in patient onboarding, benefits verification, prior authorization, document intake, and patient and provider engagement.
The AI Engineer V (Principal) shapes AI direction at the enterprise level, solves the company’s most complex and ambiguous technical problems, and sets the architecture, evaluation standards, and responsible AI practices for all AI work at Assist Rx. The role serves as a trusted advisor to engineering and executive leadership, represents Assist Rx’s AI capabilities with clients, partners, and auditors, and develops the next generation of AI technical leaders. The Principal AI Engineer partners closely with Software Engineering, Product, Architecture, Data, Security, Compliance, and Client Services, and is accountable for the quality, performance, cost efficiency, and safe and compliant use of AI with protected health information across the enterprise.
Responsibilities AI Strategy & Solution Design Define the multi-year AI technical strategy and roadmap in partnership with the Vice President, Engineering, Product, and Architecture, aligning AI investments to business value, feasibility, and risk
Lead the design of the most complex enterprise-scale AI and machine learning solutions, including generative AI,



predictive models, and intelligent document processing that span multiple platforms, products, and clients
Architect large language model applications using retrieval augmented generation, prompt engineering, structured outputs, function and tool calling, and agent-based orchestration
Set the patterns for agentic workflows, including task decomposition, tool and function calling, memory and state management, routing, transparent boundaries, human review checkpoints, and fallback paths for high-impact decisions such as benefits verification and prior authorization
Identify new AI opportunities and emerging technologies that create competitive advantage, and lead proofs of concept that move proven pilots to scale
Determine the right approach for each problem, including prompting, retrieval augmentation, tool use, task-specific models, and conventional software or deterministic logic when a model is not the right answer
Set the standard for design documentation of AI features, covering intended behavior, context and retrieval design, prompt and agent structure, evaluation approach, and fallback behavior
AI Foundations & Platform Own the enterprise AI reference architecture, platform strategy, and engineering standards, including model access, prompt and version management, and retrieval services, and ensure their adoption across all engineering teams
Lead evaluation of commercial models, AI platforms,



and vendor tools, and make build-versus-buy recommendations to executive leadership based on quality, cost, security, strategic fit, and time to value
Guide vendor and cloud provider relationships from a technical perspective, including model selection, capacity, pricing, and risk
Anticipate scaling, reliability, and cost challenges in AI systems, and lead architectural investments that address them before they affect clients
Model Development, Evaluation & Optimization Set organization-wide targets for accuracy, groundedness, hallucination rate, task completion, latency, and cost, and guide model selection, tuning, and evaluation against them
Define the evaluation strategy, benchmark datasets, and automated test frameworks used across the organization to measure output quality and detect regressions before each release
Guide optimization of retrieval pipelines, embeddings, chunking strategies, and inference performance to improve quality and reduce cost per transaction at scale
Direct error analysis and human-in-the-loop review programs with operations and clinical subject matter experts, and ensure findings drive improvement of prompts, models, and guardrails
Establish the experimentation approach, including A/B testing across prompts, retrieval configurations, model selection, and workflow design
Define and enforce quality gates and regression thresholds so AI features must meet defined accuracy and safety criteria before release
Data Engineering & Integration Set the technical direction for the pipelines that prepare structured and unstructured healthcare data, such as enrollment forms, payer documents, and clinical notes, for training, retrieval, and inference
Partner

📌 Ai engineer v (Winnipeg)
🏢 AssistRx
📍 Winnipeg