We are working with a pioneering technology firm specializing in cutting-edge AI and data solutions. This company is at the forefront of developing high-performance, GPU-accelerated applications that push the boundaries of what's possible in data processing and artificial intelligence.
The Role
- Develop and integrate data pipelines using Python.
- Deploy GPU-accelerated inference services, particularly with NVIDIA NIM.
- Build robust data pipelines for processing large volumes of documents and files (OCR, document AI).
- Configure and size GPUs for optimal inference performance (memory, batch size, concurrency, MIG/MPS).
- Utilize containerization (Docker) and orchestration (Kubernetes) for GPU scheduling.
- Implement parallel/concurrent processing for high-throughput data pipelines.
What You'll Need
- Bachelor's or Master's degree in Computer Science, Engineering, or a related field.
- Strong proficiency in Python for pipeline and integration development.
- Hands-on experience with NVIDIA NIM is essential.
- Experience building data pipelines and processing large volumes of data.
- Solid understanding of GPU configurations for inference.
- Experience with Docker and Kubernetes, including GPU scheduling.
What's On Offer
- Opportunity to work on advanced AI and data projects.
- Engage with cutting-edge NVIDIA technology.
- Be part of a dynamic and innovative team.
Apply via Haystack today!
US
