Ir al contenido principal
LLM Engineer — legal copilots
LLM Engineer — legal copilots
Harvey
Este anuncio está pensado para talento nativo en IA : habilidades y herramientas claras para saber si encajas antes de aplicar — y para reducir descartes por desajuste.
3 habilidades 1 herramienta
Compartir este rol
Copiar enlace
Modalidad Hybrid
Ubicación 575 Market Street, San Francisco, CA 94105, United States · Hybrid
Compensación $190k–$260k + equity Nivel de experiencia Beneficios Top-tier comp, equity. Cómo aplicar Legal or citation-heavy RAG example.
Publicada 13 jul 2026 Harvey is hiring a Senior LLM Engineer — legal copilots on the Legal AI team (Hybrid · San Francisco, United States). This is a hands-on role in LLM & generative AI —not a generic “AI enthusiast” post.
You will own LLM features, retrieval, agents, and evaluation end to end: problem framing, offline evaluation, safe rollout, and iteration from production signals. Success is measured with clear metrics (quality, latency, cost, or business KPIs)—not slide decks alone.
Harvey builds LLM copilots for law firms with strict confidentiality and citation requirements.
LLM Engineer (San Francisco): legal RAG, prompt systems, and human-in-the-loop review tooling.
What you will do
Deliver production-grade legal-domain LLM products with measurable quality, latency, and cost targets. Build offline evals and online monitoring before scaling to full traffic. Collaborate with product, design, legal, or domain experts on safe rollout. Write clear RFCs, runbooks, and postmortems for cross-team learning. What we look for
Multiple shipped ML/LLM features—not coursework-only portfolios. Strong Python, SQL, and experimentation discipline. Clear communication for remote or hybrid stakeholders. Work authorization for the listed country. Python
Production Python for data pipelines, model code, APIs, and automated tests—not notebook-only workflows.
LangChain
Orchestrating LLM chains, tools, and retrieval with observable steps and failure handling.
OpenAI API
Calling frontier APIs with retries, cost controls, prompt versioning, and safety filters.
✓ You can show evidence in your application: Legal or citation-heavy RAG example. ✓ Several of these show up in recent shipped work—not only on your CV: Python, LangChain, OpenAI API, and Vector DBs. ✓ You have owned LLM features, retrieval, agents, and evaluation in production: debugging live issues, running postmortems, and iterating from real user or business signals. ✓ You are comfortable with the hybrid rhythm (Hybrid · San Francisco, United States)—onsite collaboration when it matters, deep work when remote. ✓ You explain trade-offs (quality, cost, latency, safety) in plain language—with numbers or examples, not buzzwords. ✓ You read the full listing (comp: $190k–$260k + equity, benefits in At a glance) and your expectations align. Lo que pide la empresa
Legal or citation-heavy RAG example.
Inicia sesión con cuenta candidato para aplicar
Regístrate, añade titular y bio; luego podrás adjuntar enlace o PDF de CV en Mi cuenta antes de aplicar. Así las candidaturas quedan ligadas a tu perfil.
Sugerencias
Talento IA que podría interesarte Perfiles ordenados por solape con habilidades y herramientas de este rol — útil si contratas equipo o comparas candidatos.
Ofertas similares Otros anuncios que comparten habilidades o herramientas — útil para stacks comparables o alternativas.
LLM Engineer — telecom assistants Orange Labs
Indefinido (CDI) Tiempo completo Senior GenAI services Hybrid 4 Rue du Clos Courtel, Rennes, BRE 35512, France · Hybrid Rennes, France EUR 50k–70k/year + intéressement
AI Developer — enterprise workflow agents ServiceNow
Tiempo completo Senior Now Assist Hybrid 2225 Lawson Lane, Santa Clara, CA 95054, United States · Hybrid Santa Clara, United States USD 155k–195k/year + equity
NLP Engineer — assistant voyage SNCF Connect
Indefinido (CDI) Tiempo completo Mid Travel copilot Hybrid 1 Rue Camille Moke, Saint-Denis, IDF 93200, France · Hybrid Saint-Denis, France EUR 52k–70k/year + intéressement
Prompt Engineer — analytics copilot Contentsquare
Indefinido (CDI) Tiempo completo Mid GenAI product Hybrid 7 Rue de Madrid, Paris, IDF 75008, France · Hybrid Paris, France EUR 55k–75k/year + BSPCE
Agents Engineer — tool-use & planning H Company
Indefinido (CDI) Tiempo completo Senior Autonomous agents Hybrid 48 Rue de la Chaussée d'Antin, Paris, IDF 75009, France · Hybrid Paris, France EUR 80k–110k/year + BSPCE Ver todas las ofertas →
Título
LLM Engineer — legal copilots
Aplicar Pensado para equipos que contratan personas que trabajan con IA, no solo alrededor.
Los candidatos ven habilidades y herramientas al inicio; recibes candidaturas estructuradas en un solo panel.
Llega a profesionales de IA que buscan roles con expectativas basadas en pruebas.
Publicar oferta Orange Labs à Rennes conçoit des services GenAI telecom.LLM Engineer : assistants RAG, garde-fous français, coût/latence à l'échelle.MissionsPipelines RAG multicanal avec evals.Guardrails conformité telecom.Stack & environnementPython, LangChain, vector DB, Docker.Profil recherchéNLP français ;…
Beneficios · Hybrid Rennes, télécom, télétravail partiel.
Python LangChain NLP OpenAI API
Herramientas Vector DBs Docker
ServiceNow Now Assist brings agents and copilots to IT and HR workflows. AI Developer implements retrieval, tool-use, and guardrails for enterprise tenants.Hybrid Santa Clara: multi-tenant isolation and audit trails are mandatory.What you will doShip RAG plugins and workflow automations on Now…
Beneficios · Equity, hybrid South Bay.
Python LangChain OpenAI API
Herramientas Vector DBs Docker
SNCF Connect est l'app voyage officielle — horaires, billets et assistant pour des dizaines de millions d'utilisateurs.NLP Engineer (hybride Saint-Denis) : copilote voyage multilingue, RAG horaires, reranking et guardrails pour réponses fiables.À propos de SNCF ConnectEntité digitale du groupe SNCF…
Beneficios · Mutuelle, impact mobilité, hybrid Seine-Saint-Denis.
Python LangChain NLP OpenAI API
Contentsquare équipe plus de 1 000 marques avec analytics digitaux et un copilote IA pour insights produit.Prompt Engineer (hybride Paris 8e) : concevoir prompts, jeux d'éval et métriques qualité pour assistant analytics B2B.À propos de ContentsquareScale-up française leader experience…
Beneficios · BSPCE, assistant analytics B2B, hybrid Paris 8e.
Python LangChain OpenAI API NLP
H Company construit des agents autonomes avec tool-use, planification et mémoire pour des workflows enterprise depuis Paris.Agents Engineer (hybride Paris 9e) : orchestrer LLM, outils internes et evals rigoureuses sur benchmarks internes et publics.À propos de H CompanyScale-up IA française…
Beneficios · BSPCE, benchmarks publics, équipe recherche appliquée.
Python LangChain OpenAI API PyTorch