Runs the team day to day
In-house, owns the opening
Joined the team recently
From your own Gmail and LinkedIn.
How this role compares
One of 14 open Applied AI Engineer roles we are tracking today.
Posted 8 days ago, with 4 of the others posted since and 9 still open from before.
Counted across the roles Frontrunner has open right now.
About the role
This is a full-time, fully remote role for an applied AI engineer who designs, builds and tests the AI conversations and agents inside learner-facing products. It suits an engineer comfortable with prompt design, structured outputs and LLM application logic, who can also work closely with subject-matter experts. The hire is run by DistantJob, a staffing firm, on behalf of an unnamed e-learning client that builds training for professionals in regulated fields such as healthcare and finance. The work covers advisory experiences, practice simulations and diagnostic coaching, with a strong emphasis on keeping AI behavior reliable, compliant and testable.
What you’ll do
- Turn scenario specs, decision models and assessment rubrics into prompts, application logic and testable behavior.
- Identify missing requirements and technical constraints, and raise them with product, engineering and subject-matter experts.
- Define how models connect to application services and approved data sources, including APIs, tools, validation, error handling and permitted actions.
- Design prompts, structured outputs and validation layers that stop invalid responses before learners see them.
- Build conversational runtimes with controlled personas, session state and explicit state transitions.
- Keep simulation, assessment and feedback logic separate so that feedback cannot change assessment results.
- Implement grounded retrieval from approved sources, with source references where required.
- Version code, prompts, schemas and evaluation assets, and document them.
- Run bounded experiments with product, move validated prototypes into production with engineering, and help build compliance controls such as issue flagging, review steps, disclosure and logging.
What they’re looking for
- Expert prompt and context engineering, including system prompts, few-shot examples, prompt chaining and task decomposition.
- Structured outputs with JSON Schema, function calling and validation layers with retry and fallback logic.
- RAG design covering chunking, metadata filtering, hybrid search, reranking and citation grounding.
- Experience with token budgets, prompt caching and long-session memory.
- Agentic systems experience, including tool use, planner-executor patterns, orchestration, state machines and human-in-the-loop checkpoints.
- Defining tool schemas, permission scopes and action limits for agents.
- AI evaluation with golden datasets, rubric-based scoring, LLM-as-judge calibrated against human raters, and regression testing.
- LLM observability and tracing, plus awareness of security risks such as prompt injection, data leakage, jailbreaks and unsafe tool actions.
- Python or TypeScript with API integrations and automated testing.
- Git, reproducible tests and CI, and comfort working with AI coding agents.
- Ability to explain technical trade-offs to non-technical colleagues, and sound judgment on privacy, human oversight and the limits of AI-generated assessment or advice.
- Hands-on experience building multi-step conversational LLM workflows and collaborating with subject-matter experts.
Nice to have
- Background in learning products, assessment, simulations or regulated professional content.
What’s on offer
- A fully remote, full-time, long-term engagement.
- The page describes DistantJob as acting as employer of record in the candidate's country, handling contracts, payment and HR needs.
Skills
Questions about this role
Is this role remote?
Yes. It is listed as fully remote, with the location given as anywhere.
What languages and skills are needed?
Python or TypeScript, with API integrations and automated testing, is required.
Is the role full time?
Yes. The posting lists it as full time and long term.
Is prior e-learning experience needed?
It is preferred rather than required. Background in learning products, assessment, simulations or regulated content is listed as a plus.