[Remote] ML / AI Engineer (LLM and NLP Systems)

Note: The job is a remote job and is open to candidates in USA. Discernis builds AI systems that help legal teams understand massive document sets faster and more accurately. The role involves leading the design and evolution of AI systems, focusing on LLM orchestration, retrieval pipelines, and structured information extraction over large scale legal document corpora. Responsibilities • Design and productionize LLM powered pipelines for document analysis, entity extraction, issue identification, and insight generation • Advance our multi step retrieval and reasoning workflows over large, heterogeneous document collections • Own integrations across multiple model providers and self hosted inference infrastructure • Optimize inference performance, latency, and cost across hosted and self managed model deployments • Develop and refine prompts and structured outputs for complex legal and investigative use cases • Improve hybrid search quality across semantic embeddings and traditional full text retrieval • Build evaluation and benchmarking frameworks to continuously raise model quality and reliability Skills • 3+ years building production ML or NLP systems • Deep experience working with modern LLM APIs and orchestration patterns • Hands on experience with self hosted model serving such as vLLM, TGI, or similar • Strong Python skills and comfort with concurrent or distributed processing • Experience with vector search and embedding pipelines • Solid understanding of retrieval augmented generation and model evaluation • Background in legal tech, document intelligence, or information retrieval at scale Company Overview • Discernis helps law firms finish discovery faster with A.I. powered document review. It was founded in undefined, and is headquartered in New York, Delaware, US, with a workforce of 2-10 employees. Its website is