Volunteer Team: App Development Team

Volunteer Availability: Virtual

LLM engineer volunteer opportunity at iLevelUP. Fully remote, unpaid work for eligible applicants in the United States. This opening is for the Applied AI/LLM & Realtime Systems Engineer role.

LLM engineer: remote volunteer opportunity

Make AI conversations useful, responsive, observable, and dependable.

Fully remote | Unpaid volunteer | United States

About iLevelUP

iLevelUP is a free, AI-powered, game-based learning experience being developed by Believe in Me to help young people explore education and career possibilities and build self-confidence. The product is in limited beta. The learner is the main character, and iLevelUP is the guide.

LLM engineer role overview

The official role is Applied AI/LLM & Realtime Systems Engineer. iLevelUP seeks a remote volunteer LLM engineer to improve the technical systems behind its AI-supported Trail Guide interactions. You will work on the connection among model responses, retrieval, tools, speech, and application state.

The limited beta provides a foundation for disciplined iteration. Your contribution should make learner interactions more useful and reliable while giving the team evidence about quality, latency, failure modes, and operating cost.

What you will own

You own implementation and reliability for scoped AI and realtime features. Architecture decisions are coordinated with technical leadership; the AI evaluation lead owns independent evaluation criteria; privacy and safety owners define the safeguards the system must satisfy.

LLM engineer responsibilities

Review the existing orchestration and identify a small set of high-value improvements rather than introducing parallel infrastructure without a clear need.
Implement model and tool routing, structured outputs, validation, timeout handling, bounded retries, and safe fallbacks.
Improve retrieval quality through source selection, chunking, relevance checks, freshness handling, and traceable answers; distinguish retrieved evidence from model inference.
Design context and memory behavior with explicit scope, cross-user isolation, minimization, and deletion requirements reviewed with the privacy owner.
Improve streaming and speech interactions, including interruption, turn-taking, reconnection, cancellation, and clear recovery when an upstream service fails.
Enforce tool authorization and input boundaries in application code. Coordinate prompt-injection defenses and high-risk scenarios with security and AI evaluation contributors.
Instrument latency, errors, retrieval outcomes, evaluation results, and token or usage cost without placing unnecessary learner information in logs.
Deliver reviewed code, automated tests, evaluation comparisons, deployment and rollback notes, and runbooks that future contributors can maintain.

Early deliverables

First 30 days: document the current AI interaction flow, reproduce a priority quality or reliability problem, and propose a bounded implementation plan.
By 60 days: ship an approved improvement with tests, evaluation results, and measurements of latency and failure handling.
By 90 days: establish repeatable monitoring and regression checks for the feature and document operating limits, rollback, and follow-up priorities.

LLM engineer required qualifications

Practical experience shipping or prototyping integrated LLM applications using APIs, retrieval, structured outputs, or tool calling.
Strong Python, JavaScript, or TypeScript skills and experience with asynchronous services, error handling, and version control.
Ability to design and interpret evaluations rather than judging quality from a few successful demos.
Understanding of authorization, secrets management, sensitive-data handling, and common AI application risks.
Ability to debug across model, application, data, and network boundaries and communicate tradeoffs clearly.

LLM engineer helpful experience

How we work

Work in small, reviewed increments with technical leadership, product, data, character motion, and AI evaluation contributors. Use approved test environments and synthetic or minimized data when investigating issues.

Why volunteer with iLevelUP

Contribute to a nonprofit education product at a stage when your decisions can shape the learner experience.
Own a meaningful body of work and collaborate across education, design, engineering, and student support.
Develop work samples and share approved contributions in your portfolio while respecting project and learner confidentiality.

Time commitment and location

Fully remote and unpaid. Plan for a sustained contribution, with weekly availability, initial deliverables, and commitment duration agreed during onboarding.

How to apply

Apply for the Applied AI/LLM & Realtime Systems Engineer volunteer role. Use the Believe in Me volunteer application. Share your résumé or LinkedIn profile, relevant work samples, weekly availability, and why this role interests you. Share only authorized materials and remove personal, confidential, or proprietary information.

Include a repository, architecture diagram, demo, or sanitized case study. Describe an LLM or realtime feature you built, a failure you diagnosed, and how you measured the improvement.

We welcome applicants from varied backgrounds and pathways. Demonstrated capability, judgment, and dependable collaboration matter more than a particular degree. If you need an accommodation for the application or interview process, contact us through iLevelUP’s contact page.

Role details

Role: Applied AI/LLM & Realtime Systems Engineer
Program: iLevelUP, a Believe in Me initiative
Employment type: Unpaid volunteer
Workplace: Fully remote
Applicant eligibility: United States
Team: App Development Team
Company address: 107 Spring Street, 2nd Floor, Seattle, WA 98104
Job ID: 1018

Fully remote and unpaid. Plan for a sustained contribution, with weekly availability, initial deliverables, and commitment duration agreed during onboarding.