The AI product engineer uses the latest inference techniques whether that be flow engineering, RAG, multi agent architectures, whatever it takes. This engineer is an expert on using LLMs and ideally has built a RAG themselves.
Role Definition:
- Implements cutting-edge inference techniques (flow engineering, RAG, multi-agent architectures)
- Manages and improves internal benchmark for bug solving
- Builds and optimizes RAG systems and prompt engineering
- Design, develop, and implement AI-driven features and products
- Collaborate with cross-functional teams to define product requirements and specifications
- Write clean, efficient, and maintainable code
- Conduct research on the latest AI technologies and methodologies
- Optimize AI models for performance and scalability
- Participate in code reviews and contribute to best practices
- Troubleshoot and debug issues in AI systems
- Document technical specifications and processes
Requirements:
- 2-3+ years of software engineering experience-Python, Java, Typescript, etc
- 1+ year of professional LLM experience or equivalent side projects/open-source contributions
- Experience with RAGs and prompt engineering
- Proficiency with AI coding tools
- Coding experience (not just LLM expertise)
Nice-to-Have:
- Startup experience
- Tenure at a competitive tech company
- Open source LLM project contributions
This role will be onsite 5 days per week in Downtown San Francisco. Please do not apply if you are not able to be on site.
