AI / ML Engineer (Unpaid for OPT Credit)

Who We Are

ReferU.AI is the “Tinder for Finding an Attorney.” We help people with legal needs connect with attorneys who have demonstrable experience in similar legal matters, grounded in real court records. At ReferU.AI, people describe their legal issue to Link, our intake agent, and search for attorneys who have experience on similar cases. Link searches over 6 billion court dockets and filings, along with rulings, opinions, and other objective data, to surface attorneys with documented experience representing highly similar cases.

Our mission is: Smarter Results. Better Representation. The Best Outcomes. ReferU.AI is a bootstrapped public benefit corporation, founded in Houston, Texas, in 2024. We support the ReferU.AI Foundation, a nonprofit that provides low- to no-cost experienced legal representation for children in court.

ReferU.AI has been featured in the Associated Press, MarketWatch, Morningstar, Yahoo Finance, and USA Today, and was recognized among The Silicon Review’s 30 Most Innovative Companies to Watch in 2026 and in the Legal Tech & Innovation Awards. We are a small team, and we are motivated by the direct link between the code we ship and our impact on users’ lives.

Life at ReferU.AI

Remote-First Freedom & Flexible Schedules:

ReferU.AI is a diverse and globally distributed team with no plans to return to a physical office. We are fully remote with flexible work hours and an async-first communication culture so you can design your most productive workday.

Deep Work & Maker Time:

We protect engineering focus time through no-meeting blocks, written-first discussions, and clear decision logs. The expectation is impact and shipped value, not hours spent in meetings.

High-Access Leadership & Company Rituals:

You’ll have direct, regular access to leadership and visibility into where the company is going:

• Quarterly Town Halls with the Founder & CEO to walk through strategy, metrics, and milestones.
• Quarterly Demo Days where teams showcase what they’ve shipped and what they’re experimenting with.
• Monthly 1:1s with the Founder & CEO, focused on your career development, not status updates.

Collaboration, Autonomy and True Ownership of Outcomes:

You’ll work closely with product, engineering, go-to-market, and legal experts in small, highly autonomous squads. You’ll be trusted to own projects end-to-end, ask good questions, and iterate quickly while having rapid feedback and support from leadership.

Learning Culture & Monthly Learning Circles:

We’re intentional about learning together, not just alone in docs and repos:

• Monthly Learning Circles where teammates demo a new tool, technique, or experiment to cross-functional teams (engineering, product, legal, GTM).

Growth Opportunities & Promoting from Within:

We bias heavily toward promoting from within. All of our current W-2 employees started as unpaid interns and grew into expanded roles as the company scaled. You’ll have:

• Clear opportunities to take on larger projects, own systems end-to-end, and grow your scope.
• A front-row seat to how responsibilities evolve as we grow headcount, revenue, and product surface area.

Who You Are

• A recent graduate and AI/ML engineer with experience shipping production-grade LLM applications that serve real users, not just prototypes or toy examples.
• Experienced in building LLM-powered products end to end, including retrieval-augmented generation (RAG), agent and tool-calling workflows, and the evaluation systems that keep them reliable.
• Strong in Python and comfortable owning services from design through deployment, monitoring, and iteration.
• Excited about conversational intake experiences, and about making AI systems accurate, safe, and trustworthy in a high-stakes legal setting.
• Curious about retrieval, evaluation, and how people find the right attorney, even if you don’t have prior legal domain experience.
• Energized by working in a fast-paced, early-stage startup where you’ll wear multiple hats, navigate ambiguity, and make decisions quickly.

Our Tech Stack

You don’t need to know everything on day one, but you should be excited to work with (and learn) most of this stack:

• Backend & APIs: Python, FastAPI, Uvicorn, and Pydantic.
• Frontend & UX: React and TypeScript (built with Vite and Tailwind CSS).
• Orchestration & Agents: CrewAI for multi-agent orchestration on Link, and NVIDIA NeMo Guardrails for conversational safety.
• AI / LLM Providers & Libraries: OpenAI GPT models, Google Gemini, and LangChain with LangSmith for tracing and evaluation.
• Messaging: Twilio for phone verification.
• Data & Storage: PostgreSQL on Google Cloud SQL.
• CRM & Business Integrations: Salesforce CRM (REST API integration, Apex, and Lightning Web Components), and Stripe billing.
• Cloud & Infrastructure: Google Cloud (GCP), including Cloud Run, Cloud Build, Artifact Registry, Secret Manager, Cloud Tasks, and Cloud Storage, plus Docker and GitHub / GitHub Actions for CI and security scanning.
• Analytics & Logging: PostHog product analytics and Google Cloud Logging to understand usage and model behavior.

Qualifications

Required:

• M.S. in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a closely related field, recent graduate.
• Experience building and shipping production LLM applications in Python.
• Hands-on experience with FastAPI or a similar Python web framework, REST APIs, and PostgreSQL.
• Experience with LLM APIs such as OpenAI or Google Gemini, including prompt design, tool calling, and agent frameworks such as CrewAI or LangChain.
• Experience adding guardrails and evaluations to conversational AI so it stays accurate, safe, and on task.
• Experience with Docker, Git, GitHub pull request workflows, and CI pipelines, and comfort deploying services to a cloud platform.
• Daily, hands-on use of AI coding tools such as Cursor, Codex, or similar, along with the judgment to review, test, and own AI-generated code.
• Working knowledge of the Model Context Protocol (MCP), including connecting tools, APIs, and data sources to AI agents.
• Comfort working alongside AI agents as teammates, including Grok Bot, which our team uses for pull request review, QA, and project management.
• Clear written communication for an async-first, fully remote team.

Nice-to-Haves:

• Experience building conversational AI experiences.
• Experience with Google Cloud Platform services such as Cloud Run, Cloud Build, and Cloud SQL.
• Experience integrating with Salesforce or other CRMs, or with legal practice-management tools.
• Experience with Twilio or other messaging and phone verification APIs, and with Stripe or other billing integrations.
• Familiarity with application security practices and tooling, such as Bandit, Semgrep, TruffleHog, and CodeQL.
• Familiarity with TypeScript and React (with Vite and Tailwind CSS) so you can collaborate closely with frontend engineers and designers.
• Experience with product analytics tools such as PostHog to connect model changes to user outcomes.
• Background in NLP, ranking, or recommendation systems, which power how we match cases with the right attorneys.
• Interest in the legal industry and in making it easier for people to find the right attorney.

What You'll Do

AI/ML Engineering on Link:

• Build and improve the AI that powers Link, our consumer intake and attorney matching product in production at referu.ai, from conversational intake through matching consumers with attorneys who have handled similar cases.
• Improve the matching and ranking logic that connects people with attorneys who have handled similar cases.
• Design and improve RAG pipelines: chunking, retrieval, ranking, and context assembly.
• Build and orchestrate agents and tool-calling workflows, with guardrails that keep conversations safe and on task.

Prototype to Production:

• Move quickly from experiments and prototypes to reliable, maintainable production services on Cloud Run.
• Own testing, monitoring, and deployment for the systems you build, and help raise the team’s engineering standards.

Data & Ingestion Work:

• Build ingestion and processing for the data behind intake and attorney matching, including case records, intake conversations, and other unstructured documents.
• Design schemas, embeddings, and features that make retrieval and reasoning more accurate and robust.

Evaluation & Experimentation:

• Design and run evaluations that measure model quality, retrieval performance, and user-facing outcomes.
• Build evaluation suites and dashboards that track quality over time (e.g., accuracy, groundedness, hallucination rate), and use product analytics to connect model changes to user outcomes.

Cross-Functional Collaboration:

• Work with product, design, and legal experts to understand user needs and turn them into concrete technical plans.
• Participate in sprint planning, code reviews, and technical discussions as part of a small, high-ownership team.

Compensation

Employment type: Unpaid. This role is unpaid.

Americans with Disabilities Act (ADA)

ReferU.AI will provide reasonable accommodations during the application process upon your request as required to comply with applicable laws. If you have a disability and require assistance in this application process, please email joel@referu.ai.

EEO Policy Statement

At ReferU.AI, we celebrate diversity and are committed to creating an inclusive environment for the benefit of our employees, our company, and our community. As such, ReferU.AI is proud to be an equal opportunity workplace. We do not discriminate on the basis of race, color, religion, sex (including pregnancy, gender identity, and sexual orientation), parental status, national origin, age, disability, genetic information (including family medical history), political affiliation, military service, or other non-merit based factors.