Senior Software Engineer, Fullstack - New Verticals

Harvey Harvey · AI Frontier · New York, NY · Engineering

Senior Fullstack Engineer to embed with enterprise customers, build and productionize custom LLM-powered workflows, integrate with client systems, and develop evaluation frameworks for AI solutions. This role focuses on taking cutting-edge AI systems and turning them into reliable, scalable, and observable production-grade workflows.

What you'd actually do

  1. Embed with customers to map out workflows, de‑risk constraints, and define crisp success metrics for custom builds.
  2. Design → prototype → productionize custom workflows: customize knowledge sources and retrieval pipelines, tool use/agents, prompts, and guardrails; then harden them for reliability, observability, and scale.
  3. Integrate workflows with clients systems (DMS, KM, ticketing, identity/SSO) and data sources; standing up secure connectors to the rest of the Harvey platform.
  4. Build and maintain evals & harnesses that capture real‑world quality on a client-by-client basis, wiring those signals into iteration loops and model choices.
  5. Operationalize adoption: run training, write crisp runbooks, and hand-off durable playbooks to customer champions—and to Harvey product/eng—so wins scale beyond one account.

Skills

Required

  • 5+ years building and operating production software
  • Experience building LLM-powered applications
  • Customer-facing experience
  • Experience with evals
  • Fullstack development

Nice to have

  • Knowledge of legal or professional services workflows
  • Experience with enterprise systems (DMS, KM, ticketing, SSO)

What the JD emphasized

  • production software with meaningful 0→1 ownership and the ability to operate under ambiguity
  • Experience building LLM‑powered applications (retrieval, tools/agents, structured outputs, prompt/runtime safety) and taking them to production.
  • Practical experience with evals (designing task suites, pipelines, and dashboards that reflect user quality); you use evals to drive model/product decisions.

Other signals

  • customer-facing AI solutions
  • productionizing LLM applications
  • building and maintaining evals
  • integrating with client systems