LLM Application Engineer

About the role

Build the intelligence layer that powers AI experiences, working at the intersection of Large Language Models (LLMs), software engineering, and product design. Own problems end-to-end, from designing agentic workflows to improving model behavior in production.

Responsibilities

• Build and ship LLM-powered applications and AI agent workflows.
• Design systems for reasoning, planning, memory, and multi-step execution.
• Integrate LLMs with APIs, databases, and external tools.
• Develop prompting, context engineering, and tool-calling techniques.
• Build evaluation frameworks to measure AI quality and reliability.
• Optimize systems for quality, latency, and cost.

Requirements

• Artificial Intelligence (AI) experience required.
• Strong software engineering fundamentals with experience building AI-powered applications.
• Hands-on experience with LLMs, generative AI, or agent-based systems.
• Proficiency in Python, PyTorch, JAX, and vector databases.
• Ability to write clean, production-quality code.