Prompt Engineer / AI Integrations

Key Responsibilities

• Design, test, and iterate on prompts and prompt chains for production LLM features
• Build and maintain retrieval-augmented generation (RAG) pipelines and integrations
• Develop evaluation frameworks to measure prompt quality, accuracy, and safety
• Integrate LLM APIs (OpenAI, Anthropic, open-source models) into product workflows
• Collaborate with product managers to define AI feature requirements and success criteria
• Monitor and improve AI feature performance, latency, and cost efficiency
• Stay current with rapidly evolving LLM capabilities, tools, and best practices

Required Skills & Experience

• 2+ years of experience building software, with at least 1 year working with LLMs or NLP
• Proficiency with Python and experience calling LLM APIs programmatically
• Hands-on experience with prompt engineering techniques (chain-of-thought, few-shot, system prompts)
• Familiarity with RAG architectures including vector databases and embedding models
• Understanding of LLM limitations (hallucinations, context windows, token costs)
• Experience with evaluation and testing of AI outputs (both automated and human-in-the-loop)
• Strong written communication skills for crafting clear, effective prompts

Nice-to-Have

• Experience with LLM orchestration frameworks (LangChain, LlamaIndex, or Semantic Kernel)
• Familiarity with fine-tuning or distillation of language models
• Background in NLP, information retrieval, or computational linguistics
• Experience with AI safety, content moderation, or responsible AI practices
• Knowledge of cost optimization strategies for LLM-based applications

Tech Stack

What We Offer

• Competitive salary and equity package
• Flexible remote or hybrid work arrangement
• Health, dental, and vision insurance
• Annual learning and development budget
• Generous PTO policy

Interview Process

1. 1Recruiter phone screen (30 min)
2. 2Technical screen: prompt engineering concepts and LLM fundamentals (45 min)
3. 3Take-home exercise: design a prompt system for a given use case (2-3 hours)
4. 4Live walkthrough and iteration on take-home solution (60 min)
5. 5Product thinking and culture fit interview (30 min)