Proofs is a well-funded, pre-seed stage startup leveraging AI agents for code generation to boost sales engineering teams’ productivity by enabling them to build great software more efficiently and at a faster pace.

Overview

As an AI Research Engineer, you will be a core member of our Engineering Team, playing a critical role in shaping and building our product alongside a small team of extremely talented and experienced colleagues.

What we’re building

https://www.youtube.com/watch?v=TVzQ6eX36NA

Skills and Experience

  • 4+ months of experience in building LLM-driven RAG systems, preferably in the code generation space either commercially or as side projects. Open-source contributions or papers in the field are a major plus.

  • 10+ years of experience in software engineering and research.

  • 5+ years of experience in Python.

  • 3+ years of experience in any Data Science + Machine Learning stack.

  • Very strong reasoning and problem-solving skills.

  • Demonstrated ability and eagerness to quickly get up to speed with unfamiliar environments, frameworks, concepts, and programming languages.

  • Experience in independently architecting and implementing complex systems.

  • Proven capacity to work in a fast-paced, dynamic startup environment.

  • Excellent communication skills and the ability to clearly explain complex concepts.

  • Strong programming skills, experience with best practices, and proven intuition in picking the right approach, tool, framework, and mental model for the job, time, and context.

  • Contributions to open-source projects or research communities are a plus.

Responsibilities

  • Work at the forefront of AI-driven code generation and software development more broadly.

  • Contribute to and evaluate new ideas coming from the team or research community in the context of our platform.

  • Improve the evaluation toolchain to accommodate new research themes.

  • Communicate research findings and conclusions to the rest of the team, proposing new solutions.

  • Design and execute experiments to evaluate the performance, scalability, and robustness of code generation workflows, and continuously iterate to improve their accuracy, efficiency, and developer experience.

  • Closely collaborate with product and engineering teams to fully understand the business context, needs, and impact of your work, as well as provide insights.

  • Research, develop, and maintain internal tooling necessary to continuously improve the way you work.

  • Actively participate in the AI research community, staying up to date with the latest AI technologies and their applicability to our products.

Personality

  • 🔍 Detail-oriented (you know what matters) and goal-focused (and you know what doesn’t).

  • 🔩 Researcher/Tinkerer nature: Driven by curiosity and complex challenges, you delve deep into understanding and improving systems.

  • 🧠 Independent thinker: You often do not agree with the most popular opinion, and you have your arguments to back it up.

  • 🔦 Attention: Other than the above, it is all we need.

Benefits

  • Awesome Team: Work with a team of amazingly talented and experienced people.

  • ESOPs: Own part of our dream! Get an ESOP of 0.25% or more.

  • Vacay Mode On: 25 days of PTO to recharge your superpowers.

  • Remote: We're 100% remote.

  • Offsites: Who said all work and no play? Join our adventurous offsites.

  • Hardware: We’ll get you what you need.

  • Subscriptions: All necessary AI tools and subscriptions for use and/or research.

Location

Global

Job Overview
Job Posted:
5 months ago
Job Expires:
Job Type
Full Time

Share This Job: