Prompt Engineer / AI Engineer

HyperFi•San Francisco, CA

98d

About The Position

We're looking for a Prompt Engineer / AI Engineer to join early. Someone who knows how to move from prototype to production, who can design prompts, evaluate them, and wrap them in real workflows that run reliably. You’ll work closely with the CTO and Tech Lead to build intelligent systems that plug into a larger product — not just toy demos. If you’re fluent in RAG, LangChain, and PySpark, and care about real-world agent behavior, this is your kind of role.

Requirements

5–7 years building production-grade ML, data, or AI systems
Strong grasp of prompt engineering, context construction, and retrieval design
Comfortable working in LangChain and building agents, not just chains
Experience with PySpark and Databricks to handle real-world data scale
Ability to write testable, maintainable Python with clear structure
Understanding of model evaluation, observability, and feedback loops
Excited to push from prototype → production → iteration
Confident English skills to collaborate clearly and effectively with teammates

Nice To Haves

Have built agent-like workflows with LangGraph or similar
Have worked on semantic chunking, vector search, or hybrid retrieval strategies
Can walk us through a real-world prompt failure — and how you fixed it
Have contributed to OSS tools or internal AI platforms
Think of yourself as both an engineer and a systems designer

Responsibilities

Build agentic LLM pipelines using LangChain, LangGraph, and LangSmith
Design and iterate on prompt strategies, with a focus on consistency and context
Construct retrieval-augmented generation (RAG) systems from scratch
Own orchestration of PySpark and Databricks workflows to prepare inputs and track outputs
Instrument evaluation metrics and telemetry to guide prompt evolution
Work alongside product, frontend, and backend engineers to tightly integrate AI into user-facing flows