How did you hear about us?

How did you hear about us?

Role Overview

You’ll help build the core systems that make Limy work. From prompt design and retrieval pipelines to model testing and API integrations, your work will power how brands become the answer across AI platforms.

Responsibilities

  • Design and build systems that optimize how prompts interact with large language models

  • Develop tools for evaluating and tracking model responses across OpenAI, Claude, Gemini, and others

  • Integrate AI APIs and embedding models into real-time product flows

  • Work closely with product and data teams to translate user goals into intelligent outcomes

  • Experiment, iterate, and refine — always pushing for smarter, simpler solutions

Required Qualifications

  • Strong experience working with LLMs, NLP pipelines, or vector-based search

  • Proficient in Python and familiar with tools like LangChain, LlamaIndex, or Hugging Face

  • Ability to think clearly through ambiguity and build fast, testable systems

  • Comfortable navigating both research ideas and production constraints

  • Deep curiosity about how models retrieve, rank, and respond

Bonus

  • Have built internal tools for prompt evaluation or model experimentation

  • Understand the mechanics of RAG pipelines and prompt injection handling

  • Have experience with AI-first product teams and love shipping real things

How did you hear about us?

Role Overview

You’ll help build the core systems that make Limy work. From prompt design and retrieval pipelines to model testing and API integrations, your work will power how brands become the answer across AI platforms.

Responsibilities

  • Design and build systems that optimize how prompts interact with large language models

  • Develop tools for evaluating and tracking model responses across OpenAI, Claude, Gemini, and others

  • Integrate AI APIs and embedding models into real-time product flows

  • Work closely with product and data teams to translate user goals into intelligent outcomes

  • Experiment, iterate, and refine — always pushing for smarter, simpler solutions

Required Qualifications

  • Strong experience working with LLMs, NLP pipelines, or vector-based search

  • Proficient in Python and familiar with tools like LangChain, LlamaIndex, or Hugging Face

  • Ability to think clearly through ambiguity and build fast, testable systems

  • Comfortable navigating both research ideas and production constraints

  • Deep curiosity about how models retrieve, rank, and respond

Bonus

  • Have built internal tools for prompt evaluation or model experimentation

  • Understand the mechanics of RAG pipelines and prompt injection handling

  • Have experience with AI-first product teams and love shipping real things