Develop, deploy, and maintain AI Gateway and related generative AI services
Implement integrations with Cloud Management System, Portal, and other internal or external platforms using modern API protocols
Configure, deploy, and optimize LLMs and AI pipelines for production workloads
Collaborate with coworkers in the AI & Data team and other engineering groups to integrate AI services across the cloud platform
Contribute to CI/CD pipelines, automation, and operational processes for AI services
Maintain and operate AI infrastructure on Linux systems with proper monitoring and observability
Develop services using TypeScript, Python, PHP, and Rust, with a strong willingness to learn new languages as required
Participate in code reviews, unit testing, and documentation
Support workflow automation and integration with tools such as n8n and related open-source projects

Advanced expertise in generative AI with a strong foundation in programming (Python, TypeScript, PHP, or Rust)
Hands-on experience deploying and optimizing LLMs
Working familiarity with Unix-based systems (Linux or macOS)
General understanding of LLMs, memory and context management, and performance optimization
Experience with prompt engineering and integration protocols (OpenAPI, MCP)
Hands-on experience with API integration and no-code/low-code development approaches
Knowledge of Linux systems, SQL, and DevOps practices
Collaborative mindset for working in cross-functional teams
Experience with workflow automation tools (n8n) and related open-source projects (e.g., Langfuse, PyTorch, Candle, Llama-CPP)
Experience contributing to open-source AI/ML frameworks
Familiarity with cloud orchestration and containerization using Kubernetes and Docker
Knowledge of GPU deployment and optimization
Experience with multimodal interfaces and data management
Knowledge of monitoring, logging, and observability for AI workloads

Generative AI Developer

Key skills