Sr Machine Learning Engineer

Job Summary

We are looking for a Senior Machine Learning Engineer to join our Search team. You will be responsible to help turn the Docusign Agreement AI engine Iris into the institutional brain of our customers agreement ecosystems. You will work on designing and building the core ML and LLM systems that transform standalone agreements into a unified, queryable knowledge graph. In parallel, you will help architect Iris's long-term memory (LTM) layer so the platform can remember prior chats, user decisions, and corrective feedback across sessions, closing the loop between our assistant and workspace experiences. If you are excited about building knowledge-graph-centric retrieval systems and evolving context layers that continuously learn from real user interactions, this role will let you shape the future of how Docusign customers reason over their entire agreement portfolio.

This position is an individual contributor role reporting to the Sr. Manager, Software Engineering.

Responsibilities

• Design and implement the core knowledge graph and schema that model agreements, addenda, amendments, and related entities as explicit nodes and edges, enabling multi-hop and hierarchical reasoning over complex contract portfolios
• Build LLM Wiki style compilation pipelines that transform newly ingested agreements into structured, interconnected markdown or graph-based knowledge bases, including concept, entity, and comparison pages that stay in sync with upstream document changes
• Develop and productionize retrieval architectures that leverage the compiled knowledge base for high-precision, multi-step question answering and navigation across corporate hierarchies
• Architect and implement Iris's long-term memory (LTM) layer, including storage, retrieval, and summarization mechanisms that persist chat history, user actions in Canvas, and administrative overrides as episodic memories over time
• Create ML and LLM components that fuse contract-centric retrieval (GraphRAG + LLM Wiki) with institutional memory (LTM) so Iris can adapt behavior based on prior decisions, exemptions, and corrections without requiring users to restate context
• Own the end-to-end lifecycle of these models and systems-from feature and schema design through training, evaluation, deployment, and monitoring-with a focus on reliability, safety, and debuggability in production environments

Job Designation

Hybrid: Employee divides their time between in-office and remote work. Access to an office location is required. (Frequency: Minimum 2 days per week; may vary by team but will be weekly in-office expectation)

What you bring

Basic

• 8+ years of professional experience in Machine Learning Engineering or Data Science, with a strong background in Software Engineering
• Experience with PyTorch or TensorFlow, specifically regarding Time Series analysis (forecasting/anomaly detection) and NLP
• Experience building applications using LLMS (RAG pipelines, LangChain, vector databases) specifically for technical domains (code analysis, log parsing)
• Experience with distributed data processing and streaming technologies (Apache Spark, Kafka, Flink)
• Experience with software engineering fundamentals (Python, C++, or Go), CI/CD for ML, and experience deploying models via APIs (FastAPI, Triton Inference Server)
• Experience building/consuming RESTful and gRPC based web-services
• Experience with cloud deployment technologies, such as Kubernetes or Docker containers
• Experience with designing and scaling fullstack or distributed backend systems

Preferred

• Experience with Elastic Search technology
• Experience with microservice architecture
• Experience shipping highly available, scalable service on Azure
• Experience with the entire software development lifecycle, including version control (git) build process, testing, and code release
• Ability to work in a dynamic, fast-moving environment

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.