Teams at Discernis

Own and improve infrastructure across cloud, customer-managed cloud, on-premises, and air-gapped environments. Package the platform as a reproducible Kubernetes bundle, operate application and GPU workloads, manage infrastructure as code and CI/CD releases, and build monitoring, logging, and alerting for restricted environments. Responsibilities also include supporting search and data infrastructure, networking, secrets, certificates, and security hardening.

Design and improve production AI workflows for legal document intelligence using agentic orchestration, prompt engineering, retrieval, and model post-training. Own LLM evaluation and benchmarking frameworks, structured outputs, self-hosted model serving, inference optimization, and customer deployments. Build reliable, efficient, explainable systems using Python and modern LLM tooling, with emphasis on quality, latency, cost, and reproducibility.

Build and improve a high-performance frontend for legal document review, including document viewing, search, annotations, citation navigation, and AI result verification. Partner with backend and AI engineers through REST APIs, support a scalable component system, and ensure accessibility, performance, consistency, and secure handling of sensitive browser data.