Applied AI​/LLM Engineer, Public Health LLMs, Consultant Asia Eastern Europe

Applied AI/LLM Engineer, Public Health LLMs, Consultant

Asia, Africa, Eastern Europe

Resolve to Save Lives (RTSL) is a global health organization that partners locally and globally to create and scale solutions to the world’s deadliest health threats. Millions of people die from preventable health threats. We collaborate to close the gap between proven, life-saving solutions and the people who need them. Since 2017, we’ve worked with governments and other partners in more than 60 countries to save millions of lives.

We work toward a future where people live longer, healthier lives, communities flourish, and economies thrive. This is an ambitious vision, and it inspires us and our partners to make progress every day.

The Digital Team at Resolve to Save Lives (RTSL) is implementing or helping to implement cutting-edge digital tools such as the Simple app , DHIS2 and Africa Covid Dashboard. We work with national and regional health organizations to accelerate progress and advancing the use of digital technologies to save lives through our approach of simplicity, speed, and scale.

Contract duration: 1 2-month consultancy , with possibility of extension based on program needs and mutual interest

Level of Effort: Full-time 100% level of effort

Location: Remote

Resolve to Save Lives is looking for an Applied AI/LLM Engineer Consultant to support our innovative team, focusing on the exciting field of Large Language Models (LLMs) in the context of Public Health. In this role, you will contribute to the design, fine‑tuning, deployment, and evaluation of AI/ML systems based on pre‑trained models (e.g., LLaMA, Mistral, GPT, Phi) that help ease the lives of healthcare workers and clinicians.

You will work closely with back‑end and mobile engineers to bring cutting‑edge AI capabilities to life.

The ideal candidate will possess the expertise to leverage existing Large Language Models (LLMs) to train and evaluate models using program‑specific clinical data (e.g., patient notes, SMS interactions, training materials or health worker feedback) and deploy within RTSL's digital health tools and global EHRs (e.g., Simple, BP Passport). Additionally, there is a strong likelihood of developing an open‑source, locally runnable, adapted LLM to address cost and confidentiality concerns.

You'll be working at the intersection of cutting‑edge AI and grassroot public health. This is an opportunity to shape the future of digital health tools that are open source, impactful, real‑world solutions for some of the most underserved populations globally. Our primary use cases for LLMs are anticipated to include (not limited to):

• Generating patient summaries specifically tailored for healthcare workers.
• A chatbot for appointment scheduling.
• Develop a predictive model to enhance and automate existing workflows.
• Optimized worklists for frontline workers.
• On‑the‑job training and ready‑reckoner tools for healthcare professionals.

The ideal candidate will perform duties and responsibilities such as, but not limited to, the following:

• Research, evaluate, and implement state‑of‑the‑art LLMs.
• Fine‑tune pre‑trained models for specific tasks and datasets.
• Develop and deploy AI applications using Python.
• Perform data manipulation and analysis using Pandas to prepare data for model training and evaluation.
• Design and evaluate prompt engineering strategies for optimizing LLM outputs in specific public health contexts.
• Collaborate with cross‑functional teams to integrate AI solutions into existing products and workflows.
• Stay up to date with the latest advancements in AI, particularly in the LLM space.
• Apply responsible AI principles, including fairness, privacy, and transparency, especially in clinical and community health settings.
• Support the implementation of AI pilots/projects at RTSL.
• Train and upskill other engineers on the team.
• Optimized models for predicting patient behavior (propensity to miss a visit, propensity to come back on their own after missing a visit, propensity to come back after missing a visit if we call them ...)
• Clear technical documentation allowing the team to reproduce and maintain models
• Train the…