data
Posted 11 hours agoConsultant, AI Engineer
at Path
United KingdomOn-site
Responsibilities
- Utilize advanced techniques (LoRA/QLoRA, DeepSpeed) to maximize accuracy on noisy, real-world mobile images.
- Architect and deploy production-grade inference pipelines using vLLM or similar engines.
- Optimize continuous batching, KV cache management, and quantization to maximize throughput while strictly maintaining our low per-page processing cost targets.
- Design architecture for both self-hosted/local cloud environments (like Linode) and on-premise hardware, keeping data sovereignty and cost efficiency in mind.
- Tune AI models for visual data optimization.
- Develop strategies for image chunking, tiling, and preprocessing to allow models to efficiently process high-resolution images and large, complex tables without losing context.
- Evaluate, select, and provision optimal cloud and on-prem GPU infrastructure to handle a target volume of 10 million forms.
Requirements
- experience forging multisector partnerships and with expertise in science, economics, technology, advocacy, and dozens of other specialties, PATH develops and scales up innovative solutions to the world’s most pressing heath challenges.
- PATH is seeking an AI Engineer to help scale SnapiForm, an AI-powered platform available through Telegram mini-app, WhatsApp and the browser that enables health workers to digitize paper HMIS forms by simply taking a photo.
- In this role, you will develop and optimize computer vision and Vision-Language Model (VLM) pipelines for handwriting recognition, table extraction, and structured data parsing, while building scalable and cost-efficient AI systems for low-resource health settings.
- Responsibilities: Design and optimize AI pipelines for complex document understanding.
- Willingness to travel to PATH countries as needed and overlap with GMT and ESA timezones Required Qualifications and
- Experience: Education : B.S. or M.S. in Computer Science, Artificial Intelligence, Machine Learning, or a related quantitative field.
- experience in Machine Learning Engineering, with at least 1-2 years specifically focused on Computer Vision, Document AI, or Multimodal Large Language Models.
- Core Frameworks : Deep expertise in PyTorch and the Hugging Face ecosystem (Transformers, PEFT).
- experience working with Document AI, Optical Character Recognition (OCR), Handwriting Recognition (HTR), or Vision-Language models.
- Image Processing : Proficiency in computer vision libraries (OpenCV, Pillow) and
- experience with Docker, Kubernetes, and cloud GPU provisioning. Familiarity with distributed training and inference optimization. Programming : Exceptional Python skills, with
- experience writing clean, modular, and highly optimized code.
- Strong focus on building cost-effective, scalable AI solutions that perform well on limited hardware.
- Able to balance cutting-edge AI research with practical engineering decisions and real-world constraints.
- Strong sense of accountability and commitment to continuous improvement.
Experience
- Experience : 7+ years of
Benefits
- PATH current employees - please log in and apply Here PATH is a global nonprofit dedicated to achieving health equity. With more than 40 years of
- Research, benchmark, and fine-tune state-of-the-art Vision-Language models (e.g., Qwen-VL) and foundational OCR models on domain-specific datasets.
- Competitive compensation and flexible working arrangements.
Additional details
- Following a successful pilot in the DRC that significantly improved data accuracy and reduced reporting time, SnapiForm is now expanding to process millions of health records each month.
- Assess next-generation hardware (e.g., NVIDIA Blackwell nodes) to balance massive scalability, performance, and budget efficiency.
- Lay the technical groundwork for future iterations, including offline/edge processing support, expanded multilingual capabilities, and interoperability beyond DHIS2.
- experience deploying models using vLLM. Domain Expertise : Proven
- Proactive and able to work independently as well as collaboratively.
- What We Offer: Opportunity to contribute to impactful digital health and data initiatives.