AI Engineer, Core Harness & LLM Systems (London)

Granola inc; Greater London; On-site; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Relocation assistance

Job summary

Granola inc is seeking a self-starting engineer to apply the latest LLM advancements to user-centric products. You’ll work on the Core Harness team, turning models into reliable agents and improving how they remember, recover from tool failures, and execute tasks.

You’ll own LLM-based features end-to-end, build evaluation frameworks, and collaborate with a cross-functional team to create a cutting-edge product in London.

Qualifications

• Engineering experience at tech and product-driven companies.

Responsibilities

• Own the development and application of LLM-based features end-to-end.
• Build and maintain evaluation frameworks for prompt iteration and semantic retrieval.
• Optimize embeddings and vector stores for performance and scalability.
• Interact with users to understand their problems and design solutions.
• Stay up-to-date with the latest trends in LLMs and applied AI practices.
• Collaborate with a cross-functional team of engineers, product managers, designers, and other members to create a cutting-edge product.

Skills

LLM solutions

TypeScript

React.js

Node.js

RAG systems

Knowledge graphs

Memory

LLM infra

Tools

OpenAI

Anthropic

Google

Prompt management

Logging/tracing

Eval frameworks

Vector stores

Job description

Granola inc is seeking a self-starting engineer to apply the latest LLM advancements to user-centric products. You’ll work on the Core Harness team, turning models into reliable agents and improving how they remember, recover from tool failures, and execute tasks.

You’ll own LLM-based features end-to-end, build evaluation frameworks, and collaborate with a cross-functional team to create a cutting-edge product in London.