About the job
Hello from Team Granola!
If you haven't yet, be sure to explore what we are creating, and discover why joining us is a great choice.
We are in search of a proactive AI Engineer who is passionate about leveraging the latest advancements in Large Language Models (LLMs) to design and develop user-centric products.
In this pivotal role, you will keep abreast of the latest LLM trends, build robust evaluation frameworks for AI features, and apply your expertise with a focus on product outcomes. As a key member of our founding team, you will engage directly with users to understand their challenges and swiftly develop features that provide substantial value. Your contributions will be crucial in driving Granola towards a significant growth milestone.
Key Responsibilities:
Lead the end-to-end development and implementation of LLM-based features.
Establish and manage evaluation frameworks for prompt iteration and semantic retrieval.
Enhance embeddings and vector stores for optimal performance and scalability.
Engage with users to identify their needs and devise effective solutions.
Stay informed on emerging trends in LLMs and applied AI methodologies.
Collaborate with a diverse team of engineers, product managers, designers, and other stakeholders to develop a cutting-edge product.
Qualifications:
Proven engineering experience in tech and product-focused organizations.
Experience in deploying multi-provider LLM-based solutions in production (e.g., OpenAI, Anthropic, Google).
Proficiency with LLM infrastructure platforms (prompt management, logging/tracing, evaluations).
Experience in designing large-context LLM systems (RAG, knowledge graphs, hybrid search, memory).
Expertise in building features end-to-end using TypeScript, React.js, and Node.js.
Personal Attributes:
Are primarily a builder with a passion for creating impactful solutions.
Excited about working in-person at our London office (most of the time).
Thrives in a startup environment, embracing challenges and opportunities.
