tl;dr

• – if you're never satisfied with your skill level, insanely hardworking, and want what you code on Monday to impact real people on Tuesday, this is for you.
• – you'll work on knowledge engines and multimodal agents for complex physical products, including expressive voice AI and codegen systems that explain what text alone can't.
• – you'll own a focused piece of that work alongside our engineers, from building and testing it to shipping it to real customers.
• – we're backed by Paul Graham, Bloomberg Beta, Burst Capital, SV Angel, Weights & Biases, and more. Position is in person in San Francisco.
• – Compensation: to be discussed.

what we're doing

Prox is building the best technical product expert for extremely complicated physical products. A multimodal agent that can draw wiring schemes, share CAD models, process incoming videos from a technician in the field, and support people over the phone with voice that can pass the Turing test.

what you'll work on

You'll take on a focused project in one of these areas:

• Knowledge Engine. Help build the core engine that stores, relates, and reasons over product knowledge: manuals, compatibility matrices, installation guides, field observations, tribal knowledge.
• Emotionally Intelligent Voice AI. Help build and test phone support where a customer calls in, describes their problem, and gets walked through a solution by an AI that understands tone, frustration, urgency, expression.
• Code Generation as a Primitive. When something is too cognitively hard to explain in words, our agent draws it. You'll help build real-time diagrams, interactive schematics, and visual walkthroughs generated through code.

working with customers

Your work will be customer facing. You'll join customer calls and demos with our team, hear directly from the people using Prox, and see where they get stuck. You'll help test your work against real product questions and explain what you've built to the people who need it.

You'll work alongside our engineers to turn that feedback into improvements, help with deployments, and follow your project after it ships. Learning to understand a customer's problem is part of the engineering work here, right alongside writing the code.

who we're looking for

You're early in your career. Maybe studying, maybe graduating, maybe an internship or two. We care about what you've built, how fast you learn, and whether you keep going when something is hard.

You don't need to know every part of our stack already. You should be able to write code, explain your decisions, take feedback, and keep improving. You'll work with our engineers to scope your project, review your code, and get it into customers' hands.

the application process

Start with our challenge: build a multimodal reasoning agent for the sample product. The agent needs to answer deep technical questions accurately, in a helpful tone, and not just in text. Submit your fork and resume below.

We'll review your submission with your experience level in mind. We care about how you approach the problem, what you build, and what you learn along the way.