AI Infrastructure & Full-Stack Engineer; PT​/Retainer — Flex - TS​/SCI Scope

Catalyst is looking for a highly skilled engineer to support the design, deployment, and optimization of our on-premises AI infrastructure. This role can be part-time, on-retainer, or structured as an independent contractor, with flexibility to expand to full-time if needed.

• Designing and maintaining on-prem AI stacks — GPU servers, local clusters, NAS storage
• Building and managing Docker/Docker Compose environments
• Optimizing model-inference pipelines for speed and reliability
• Developing backend services and APIs for AI applications
• Automating system setup and maintenance with Bash, Python, or Power Shell
• Managing GPU drivers, CUDA, and dependency stacks
• Implementing logging, metrics, and fault-tolerant distributed systems
• Integrating AI systems with local networks (DNS, SSL/TLS, reverse proxy, firewall, auth)
• Maintaining clear documentation and deployment procedures

• Strong proficiency in Python, JavaScript, and full-stack development
• Proven experience running GPU-accelerated workloads in Linux environments
• Deep knowledge of Docker, GPU runtime management, and multi-container orchestration
• Linux server administration, security hardening, and user-permission management
• Networking fundamentals (VLANs, NAT, DNS, reverse proxying)
• System performance tuning (CPU/GPU/RAM)
• Ability to read/debug code without IDE or internet access