Senior AI Software Engineer

BriefCatch
BriefCatch

Software Engineering, Data Science

New York, NY, USA

Posted on Jul 11, 2026

Who Are We?

BriefCatch is the leading legal writing software trusted by top litigators, judges, and legal teams across the country. Our platform helps legal professionals write with greater clarity, precision, and persuasive force. We’re a small, senior team building software where quality and precision genuinely matter, and we’re looking for engineers who care about the same things

The Role

We’re looking for a Senior AI Software Engineer to own meaningful parts of the product end-to-end. You’ll work across the full stack, from the document-centric UI our users live in to the backend services and AI-powered flows that drive the core BriefCatch experience. This is a high-ownership role: you’ll shape technical direction alongside a small group of senior engineers, set the bar for code quality and engineering practices, and have real influence over how we build as we scale.

What you'll do?

  • Design and ship LLM-powered legal intelligence features with extremely high accuracy requirements.
  • Lead advanced prompt engineering and iterative tuning (CoT, few-shot, ReAct, structured outputs, self-verification) specifically tuned for legal accuracy.
  • Build and continuously improve RAG pipelines over large legal data points, including chunking strategies, embedding models, reranking, and domain-specific retrieval optimization.
  • Create rigorous LLM evaluation frameworks, automated regression suites, and human review workflows focused on citation correctness and legal reasoning quality.
  • Productionize AI components: integrate cleanly with backend services (Python/FastAPI + Syncfusion), implement guardrails, caching, fallback logic, cost/latency controls, and full observability for every LLM call.
  • Apply targeted fine-tuning (LoRA/QLoRA), quantization, and inference optimizations when they deliver clear gains in accuracy or economics for legal workloads.
  • Work shoulder-to-shoulder with systems engineers, legal experts, and product to turn promising AI experiments into reliable, auditable features that lawyers and judges can trust.
  • Track the fast-moving LLM landscape and bring pragmatic, high-leverage advancements into production while maintaining BriefCatch’s high bar for accuracy and safety in legal contexts

What We're Looking For

  • 5–8 years of professional software engineering experience, including at least 1+ year building and operating production LLM or AI systems with real user impact.
  • Demonstrated expertise in prompt engineering/tuning at a high level, plus hands-on experience with major LLM orchestration frameworks (LangChain, LlamaIndex, or equivalent).
  • Strong, practical experience designing, deploying, and iterating on RAG systems and vector databases in production applications.
  • Excellent Python skills and proven ability to take LLM features from prototype to monitored, reliable production services (latency, cost, error handling, integration with existing backends).
  • Deep appreciation for AI safety, prompt injection risks, citation hallucination, and responsible deployment — especially critical in legal and high-stakes domains.
  • Track record of shipping AI capabilities that deliver measurable quality and business impact, not just experiments.

Nice to Have

  • Direct experience with legal tech, document AI, citation systems, or high-stakes reasoning domains (finance, healthcare, etc.).
  • Hands-on work with agentic workflows, tool-calling, or multi-step legal reasoning agents in production.
  • Familiarity with LLM observability tools (LangSmith, Helicone, etc.) and strong practices around evaluation, regression testing, and continuous improvement of LLM quality.
  • Open-source contributions to LLM tooling, legal NLP, or evaluation frameworks.

Why this Role

  • Established product, real users, real impact, not a research project.
  • Substantial ownership and influence as one of a small group of senior engineers.
  • You’ll go deep on AI systems, prompting, and validation in a domain where getting it right actually matters.
  • High-trust, supportive team that values craft and judgment over process.

Compensation

In accordance with the New York Pay Transparency Law (NY Labor Law §194-b) and the New York City Salary Transparency Law, the anticipated base salary range for this role is $190,000 – $240,000 per year, plus equity. Actual compensation will be determined based on experience, skills, and qualifications. This role also includes comprehensive benefits.

Equal opportunity

BriefCatch is an equal opportunity employer. We are committed to providing a workplace free from discrimination and harassment. All qualified applicants will receive consideration for employment without regard to rrace, religion, color, sex, gender identity, sexual orientation, age, non-disqualifying physical or mental disability, national origin, veteran status or any other basis covered by appropriate law. All employment is decided on the basis of qualifications, merit, and business need.

By submitting your application, you give BriefCatch Permission to email, call or text you using the contact information provided. We will only contact you with job related information.