Clera
LLM Engineer
About this role
Build production LLM systems for an AI-powered supply chain management platform at a Y Combinator–backed startup. Own the full lifecycle of LLM agents—from prototyping to deployment—that automate critical supply chain decisions for global CPG brands.
What you'll do
- Design and iterate on LLM agents that optimize production planning, facility selection, and logistics routing decisions
- Develop robust prompts, tool definitions, structured outputs, and multi-step agent workflows handling real-world supply chain data complexity
- Evaluate and select LLMs based on latency, cost, accuracy, and fit for specific supply chain use cases
- Build evaluation frameworks and maintain observability/monitoring to track production performance and enable rapid iteration
- Ship end-to-end LLM features from API integration through testing to production deployment
- Establish feedback loops and logging systems to continuously measure and improve system accuracy in live environments
What they're looking for
- Large language model (LLM) APIs (OpenAI, Anthropic, DeepSeek, Gemini)
- LLM agent design and multi-step workflow architecture
- Prompt engineering and structured output design
- Evaluation framework design for LLM systems
- Production observability, monitoring, and logging tools
- HuggingFace ecosystem
- System design for tools/functions and agent flows
- Self-hosted LLM deployment (bonus)
Benefits
- Visa sponsorship available
- High autonomy and direct business impact
- Work on greenfield LLM systems at an early-stage startup
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Clera
Clera builds an agentic operating system that automates complex workflows and processes through AI agents, with a platform designed to simplify distributed infrastructure management for developers. The company is hiring Founding Engineers, Customer Engineers, and Product Engineers to develop both backend systems and user-facing interfaces across their AI automation products.
View all jobs at CleraLikely interview questions
- Walk us through a production LLM system you shipped end-to-end—what was the hardest part of moving from prototype to production?
- How do you approach LLM model selection when latency, cost, and accuracy all matter? Give a concrete example.