Applied AI Engineer

<p><em>Teaching AI to say yes is easy. Teaching it when to say ‘no,’ ‘I don’t know,’ or ‘let me get a human’ is the actual job. Our client is hiring an Applied AI Engineer to build the second kind.</em></p> <p>&nbsp;</p> <p>&nbsp;</p> <p>The Applied AI Engineer designs, builds and tests the AI conversations and agents inside the client’s learner-facing products: advisory experiences, practice simulations and diagnostic coaching.</p> <p>They work with Product, Content Studios, Engineering and subject-matter experts. They turn product and instructional requirements into reliable AI behavior, prove it through testing, and keep it performing after release.</p> <p>This company is at the forefront of learning technologies, providing e-learning programs for professionals in regulated industries such as healthcare and finance. They’re constantly evolving and growing, run efficient Agile-first teams, and have a broadly distributed staff. They value good-natured, inquisitive, and methodical IT professionals who come prepared to collaborate and share their knowledge.</p> <p>&nbsp;</p> <p><strong>Your responsibilities will include:</strong></p> <ul data-lfile-container="1d3cefef-61e1-46d0-9ef3-00bdc885aa6b" data-pm-slice="3 3 []"> <li style="text-align: left;">Turn scenario specs, decision models and assessment rubrics into prompts, application logic and testable behavior.</li> <li style="text-align: left;">Spot missing requirements and technical constraints, and raise them with Product, Engineering and SMEs.</li> <li style="text-align: left;">Define how AI models connect to application services and approved data sources: APIs, tool interactions, data structures, validation, error handling, permitted actions.</li> <li style="text-align: left;">Design prompts, structured outputs and validation logic, and catch invalid responses before they reach learners.</li> <li style="text-align: left;">Build conversational runtimes with controlled personas, session state and explicit state transitions.</li> <li style="text-align: left;">Keep simulation behavior, assessment logic and feedback separate, so feedback cannot change assessment results.</li> <li style="text-align: left;">Implement grounding and retrieval from approved knowledge sources, with source references where required.</li> <li style="text-align: left;">Keep code, prompts, schemas and evaluation assets under version control, and document them.</li> <li style="text-align: left;">Run bounded experiments with Product, with clear questions and success measures.</li> <li style="text-align: left;">Take validated prototypes into production with Engineering, and check behavior stays the same.</li> <li style="text-align: left;">Help build the technical controls that keep AI features compliant with accreditation requirements (issue flagging, review steps, disclosure, logging).</li> </ul> <p>&nbsp;</p> <p><strong>What are the required skills?</strong></p> <ul data-lfile-container="1d3cefef-61e1-46d0-9ef3-00bdc885aa6b" data-pm-slice="3 3 []"> <li>Expert prompt and context engineering: system prompts, few-shot examples, prompt chaining, routing, breaking complex tasks into steps</li> <li>Structured outputs with JSON Schema, function calling and validation layers, with retry and fallback logic</li> <li>RAG design: chunking, metadata filtering, hybrid search, reranking, citation grounding</li> <li>Managing token budgets, prompt caching, context compaction and long-session memory</li> <li>Agentic systems: tool use, planner/executor patterns, multi-agent orchestration, state machines, human-in-the-loop checkpoints</li> <li>Defining tool schemas, permission scopes and action limits for agents</li> <li>AI evaluation: golden datasets, rubric-based scoring, LLM-as-judge calibrated against human raters, regression testing</li> <li>LLM observability and tracing</li> <li>LLM security: prompt injection, data leakage, jailbreaks, unsafe tool actions, and guardrails</li> <li>Comparing prompting, retrieval and model options on quality, latency and cost</li> <li>Python or TypeScript, including API integrations and automated testing</li> <li>Git (e.g. Bitbucket), reproducible tests and CI</li> <li>Works with AI coding agents by default</li> <li>Explains technical trade-offs to non-technical colleagues</li> <li>Sound judgment on privacy, human oversight and the limits of AI-generated assessment or advice</li> <li>Hands-on experience building LLM applications with multi-step conversational workflows</li> <li>Experience collaborating with subject-matter experts</li> </ul> <p>&nbsp;</p> <h4 data-lfile-container="1d3cefef-61e1-46d0-9ef3-00bdc885aa6b" data-pm-slice="1 3 []">Preferred</h4> <ul> <li>Background in learning products, assessment, simulations or regulated professional content</li> </ul> <p>&nbsp;</p> <p>&nbsp;</p> <p>&nbsp;</p> <p>If this looks interesting, please use the form below to apply! Remember, this is a fully remote, long-term opportunity :)</p>