Senior Generative AI Engineer
Cleary Gottlieb Steen & Hamilton LLP3 days ago
Base Salary
$200k - $240k/yr
Responsibilities
- Design, build, deploy, and monitor production LLM-powered document analysis systems for extraction, classification, and risk flagging.
- Architect multi-step and multi-agent workflows with state management, tool calling, memory, and human-in-the-loop checkpoints.
- Develop advanced RAG pipelines using chunking, hybrid search, metadata filtering, reranking, and vector-store lifecycle management.
- Build golden test sets, automated evaluation pipelines, regression suites, and governance frameworks measuring accuracy, faithfulness, and hallucination rates.
- Implement prompt firewalls, output filters, PII redaction, and other guardrails for safety, privacy, and regulatory readiness.
- Optimize latency and token costs through caching, batching, rate-limit handling, fallback logic, model selection, and observability.
- Transform legal data into structured, high-quality datasets for AI systems.
- Collaborate with lawyers and product stakeholders to define acceptance criteria, clarify workflows, and iterate based on user feedback and evaluation results.
- Write clean, tested, production-ready Python and participate in code reviews, version control, CI/CD, and feature-flagged releases.
Requirements
- At least 3 years of professional experience building and deploying AI systems, including at least 1–2 years focused on production LLM or generative AI applications.
- Deep experience with document-heavy NLP, including complex-layout PDFs, tables, scanned documents, entity recognition, and structured output generation.
- Proven ability to design and optimize production RAG pipelines and prompt architectures for accuracy, cost, and latency.
- Strong Python engineering skills and experience shipping production-ready software.
- Familiarity with an LLM orchestration framework such as LangGraph or LlamaIndex, or an equivalent framework.
- Experience with a vector database such as Pinecone, Weaviate, or pgvector, or an equivalent technology.
- Experience deploying and monitoring LLM-backed services on cloud platforms, preferably AWS or Azure, including CI/CD, containerization, and observability tooling.
- Experience designing systematic generative-AI evaluations, including automated evaluations, golden test sets, and faithfulness or hallucination metrics.
- Ability to own workstreams end to end and communicate technical tradeoffs and results to non-technical stakeholders.
- Interest in legal work; legal, document-automation, compliance-technology, or other regulated-industry experience is advantageous.
- Experience with model-serving infrastructure such as vLLM, TGI, or Triton is advantageous.
- Experience with knowledge graphs, ontologies, semantic reasoning, Spark, Databricks, published research, or significant open-source contributions is advantageous.
- A Master's or PhD in Computer Science, Computational Linguistics, Mathematics, or a related quantitative field is preferred.
Benefits
- Comprehensive benefits package including health care benefits.
- Remote-first work environment with mentorship, structured code reviews, pair programming, and weekly knowledge-sharing sessions.
- The role is exempt and not eligible for overtime pay.
- The estimated base salary range is $200,000 to $240,000 at the time of posting.
Tech Stack
Categories