Sr. Software Engineer, AI (Founding)

Department: Engineering

Location: Remote (US-based)

Compensation: Strong base + meaningful early-stage equity + benefits

The Opportunity

Complex litigation is the ultimate test of human cognition. We are building the AI that passes it. This is especially true in healthcare, where cases involve thousands of pages of medical records, conflicting timelines, and evidence requiring deep clinical context. Our platform does more than just organize data; it reads, reasons, and references across these massive corpora to produce audit-ready work in minutes. We are fundamentally redefining the mechanics of how the world’s top law firms win cases.

We have moved past the initial experimental phase. With paying customers, a product in production, and a growing pipeline, we are ready to scale our vision. As our Founding Sr. Software Engineer, you will not just follow a roadmap; you will help draw it, architecting multi-node agents that plan, reason, and act across thousands of documents to drive better legal outcomes. This is real orchestration where you own the technical standards and influence every major architectural decision from zero. Because you are a founding hire, you carry the responsibility of setting the engineering culture for everyone who follows, shipping code that directly determines the success of real case work.

The Role

As our Founding Sr. SWE, you own the translation of legal complexity into technical architecture. You will spend your time designing and implementing sophisticated agentic workflows using frameworks like LangGraph to handle non-linear reasoning tasks.

You will work directly with the founders and the Product Manager to figure out what needs to exist. You are expected to move fluidly across the stack: from backend Python services to React frontend surfaces; ensuring that the end-to-end experience for a lawyer is seamless and the reasoning behind every AI-generated claim is transparent and cited.

⚙️ The Stack

• Languages: Python, React

• Orchestration: LangGraph, Auto-Gen, Google ADK, or similar graph-based frameworks and prompt optimization techniques like DSPy

• Infrastructure: Azure Cloud or similar cloud ops such as AWS and GCP

• Data: MongoDB, vector stores (Pinecone/Weaviate), document pipelines

• Observability: LangSmith, Weights & Biases, custom eval harnesses

• LLM Ops: Continuous evaluation, prompt versioning, A/B testing in production

What You'll Ship in 90 Days

• Harden the Core: Ship a production-grade reasoning loop that successfully handles complex clinical context without human intervention.

• Build the Harness: Establish the core evaluation harness for retrieval accuracy that the rest of the engineering team will use for all future features.

• Deploy a Live Feature: Own a major feature from discovery through to production that is actively used by a top-tier defense law firm on a live case.

Who Thrives Here

You have 5+ years building production software, ideally at early-stage startups where you have a proven track record of shipping production-ready ML and LLM-based features. You care about craft, not just commits.

• You see signal where others see noise: You can cut through the complexity of a legal document to find the technical path forward.

• You are a builder: You are excited to create patterns from chaos, not just follow existing ones.

• You think in agentic graphs: You understand that LLM systems are non-linear and you architect for that reality.

• You are low ego and high speed: You stay calm when production breaks and you care more about the user's outcome than the elegance of your code.

• (Bonus) You have exposure to legaltech, healthcare, biotech, or other regulated industries where precision matters.

How We Work

We’re not just building AI for lawyers; we’re building an AI-native company. That means humans and AI collaborating across every function internally, and a bias toward automation over headcount. You’ll work alongside AI daily to write code, synthesize research, draft documentation, and move faster than teams twice our size.

We give direct feedback, we move quickly, and we trust people to own their work. There is no middle management here to provide detailed specs or hand-holding. If you need a lot of structure to be productive, this is not the right seat. If you thrive with autonomy and want to build the technical foundation of a company from the ground up, let's talk.

🚀 Why Us

• Ship Ideas Straight to Production: Your decisions move from whiteboard to a lawyer’s desk in hours, not weeks.

• Debate Architecture with Peers: Work with founders and engineers who still write code and value technical truth over process.

• Own the Standard: You aren't just joining a team; you are setting the bar for what "AI-native engineering" looks like.

• Mission-Critical Work: Every workflow you automate moves fairness closer to people who cannot afford delays.

What We Offer

• Competitive base + early-stage equity

• Full health, dental, and vision coverage

• Remote-first flexibility with optional in-person collaboration

• Direct access to frontier models and the budget to experiment

• The chance to define how AI and law work together before anyone else does