Job Description
We are building the foundational infrastructure for the autonomous enterprise of 2026. NexusCore AI is looking for a visionary Lead AI Infrastructure Engineer to architect the next generation of neural processing units and autonomous agent ecosystems.
In this role, you won't just manage servers; you will shape the future of human-AI collaboration. We are solving complex problems in latency reduction, memory-efficient transformers, and secure decentralized AI networks.
Responsibilities
- Architect and deploy scalable, high-performance inference engines capable of handling 10B+ parameter models in real-time.
- Design the neural network architecture for our proprietary Agentic Workflows, ensuring autonomous decision-making capabilities.
- Implement advanced caching strategies and quantization techniques to optimize inference costs by 40%.
- Collaborate with the security team to ensure robust, verifiable AI operations within a decentralized environment.
- Mentor a team of junior engineers and researchers in cutting-edge deep learning techniques.
- Oversee the migration of legacy monoliths to microservices optimized for 2026 containerization standards.
Qualifications
- 10+ years of experience in Systems Engineering, DevOps, or Machine Learning Infrastructure.
- Deep expertise in Python, C++, and Rust, with a focus on performance optimization.
- Proven experience deploying Large Language Models (LLMs) at scale, including RAG pipelines and fine-tuning.
- Familiarity with 2026-era technologies such as Edge AI, Neural Radiance Fields, or Autonomous Agent frameworks.
- Strong background in distributed systems, Kubernetes, and cloud-native architectures (AWS/GCP).
- Excellent problem-solving skills and the ability to communicate complex technical concepts to non-technical stakeholders.