Free Guide for Litigators: How Attorneys Can Safely Adopt AI Without Ethical Risks → Download Now

Join Litmas

Founding Full-Stack Engineer

We're seeking a Founding Engineer to join our core team and shape the technical foundation of Litmas AI. This is a rare opportunity to build a category-defining product from the ground up, working directly with the founders to create technology that will transform the US litigation market.

As a founding engineer, you'll have significant ownership over our technical architecture, product decisions, and company culture. Your code will directly impact how thousands of attorneys practice law.

What You’ll Do

  • Architect and build core platform features using Python, Node.js, Next.js, React, and MongoDB
  • Design and implement production-grade LLM systems with advanced tool usage, RAG pipelines, and agent architectures
  • Build AI workflows that combine multiple tools for legal research, validation, and document analysis
  • Create scalable RAG infrastructure to handle thousands of legal documents with high accuracy
  • Implement AI tool chains to provide agents tool inputs
  • Design intuitive interfaces that make complex legal workflows simple and powerful
  • Own end-to-end features from conception through deployment and iteration
  • Establish engineering best practices for AI systems including evaluation, monitoring, and safety
  • Collaborate directly with founders on product strategy and technical roadmap

Must-Haves

  • Deployed production-grade LLM applications with demonstrable experience in:
    • Tool usage and function calling
    • RAG (Retrieval-Augmented Generation) implementation at scale
    • Agent architectures and multi-step reasoning
    • Prompt engineering and optimization
  • Knowledge of multiple LLM providers (OpenAI, Anthropic, Cohere, open-source models)
  • Background in building AI evaluation and monitoring systems
  • Experience with document processing and OCR technologies
  • 3+ years of production experience with Node.js, Python, Next.js, and React
  • Strong MongoDB expertise including schema design and optimization
  • Experience with vector databases (Pinecone, Weaviate, Qdrant, or similar)
  • Full-stack mindset with ability to own features from database to UI
  • Track record of shipping complex web applications at scale
  • Deep understanding of LLM limitations, hallucination prevention, and validation techniques

The Ideal Candidate

You're not just an AI engineer, you're someone who understands how to build reliable, production-grade AI systems that users can trust. You've wrestled with RAG accuracy, tool reliability, and LLM hallucinations in production.

You know the difference between a demo and a system that handles real-world complexity. You're excited about applying AI to transform how legal professional’s work.

Tech Stack

Join the future of litigation

Litmas AI is an equal opportunity employer committed to building a diverse team. We encourage applications from candidates of all backgrounds.

What We Offer

Deep Technical Interview

Our process includes deep technical interviews and fit conversations.

As part of the evaluation, there will be an extensive take-home test that should expect to take at least 4-5 hours depending on your skill level.

This allows us to see how you approach real problems similar to what you’ll encounter at Litmas AI.

How to Apply

Send your resume and a note about why Litmas AI excites you to careers@litmas.ai. Include:

  • Specific examples of production LLM systems you’ve built
  • Details about your experience with tool usage and RAG
  • Links to relevant projects or GitHub repos
  • A brief note on the most challenging AI/LLM problem you’ve solved in production

We move quickly! Expect to hear back within 48 hours.