Prompt Engineer / AI Engineer

HyperFiSan Francisco, California, United States, 94102

30+ days ago

Job type

Full-time

Job description

About HyperFi

We're building the kind of platform we always wanted to use : fast, flexible, and built for making sense of real-world complexity. Behind the scenes is a robust, event-driven architecture that connects systems, abstracts messy workflows, and leaves room for smart automation. The surface is clean and simple. The interactions are seamless and intuitive. The machinery underneath is anything but. That's where you come in.

We're a well-networked founding team with strong execution roots and a clear roadmap. We're backed, focused, and delivering fast.

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.

What You'll Do

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

Tech Stack (So Far)

Python (primary language for all LLM + orchestration work)

LangChain + LangGraph + LangSmith

Databricks + PySpark for processing, labeling, and training context

Gemini + model routing logic

Postgres, and custom orchestration via MCP

GitHub Actions, GCP

There's enough here to move fast, but still plenty of room for your fingerprints.

How We Build

Engineers come first : your time, focus, and judgment are respected

Deep work >

chaos : fixed cycles & cooldowns protect focus and keep context switching low

Autonomy is the default : trusted builders who own outcomes, no babysitters

Ship daily, safely : merge early, integrate vertically, ship often, use feature flags, and keep momentum

Outcomes over optics : solve real problems, not ticket soup

Voice matters : from week one, contribute, improve something, and shape how we build

Senior peers, no ego : collaborate in a high-trust, async-friendly environment

Bold problems, cool tech : work on complex challenges that actually move the needle

Fun is part of it : we move fast, but we also celebrate wins and laugh together

What We're Looking For

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

Bonus If You :

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

Location & Compensation

Must be based in San Francisco, Las Vegas, or Tel Aviv

Full-time role with competitive comp

Flexible hours, async-friendly culture, engineering-led environment

PI9762067534d2-30511-38844593

Create a job alert for this search

Ai Engineer • San Francisco, California, United States, 94102