LLM Application Engineer
Summary
Engineer LLM-powered applications, debug AI systems, design agent workflows, and optimize quality, latency, and cost for AI-driven services.
- Build LLM-powered applications
- Debug AI systems across model prompts and backend services
- Design agent workflows
- Develop evaluation frameworks and datasets
- Implement reliable orchestration pipelines
- Improve model behavior with prompting and context engineering
- Integrate LLMs with tools and APIs
- Optimize quality latency and cost
- Orchestrate reasoning planning memory and tool use
- Set up observability tracing experimentation and continuous improvement