Back Machine Learning Engineer

• Build and maintain high-performance distributed systems to support agreement processing, understanding or creation

• Design frameworks for multi-agent systems, focusing on state management, reliability, and long-running autonomous workflows

• Architect sophisticated Retrieval-Augmented Generation (RAG) pipelines and advanced context management strategies to improve model accuracy and relevance

• Design, implement, and own comprehensive evaluation frameworks, including the construction of domain-specific evaluation sets, golden datasets, and running structured offline/online experiments to maintain a strict quality bar

• Author, version, and optimize production prompts, ensuring high semantic accuracy and robust defenses against prompt injection

• Own and execute end-to-end model fine-tuning processes to enhance feature alignment for tailored agreement use cases

• Implement robust ML pipelines and CI/CD workflows, focusing on observability, telemetry instrumentation, log parsing, and the seamless deployment of generative AI services

• Collaborate cross-functionally with Applied Science and Product Management teams via a joint triage framework to deliver AI capabilities into production-grade features

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)

Positions at Docusign are assigned a job designation of either In Office, Hybrid or Remote and are specific to the role/job. Preferred job designations are not guaranteed when changing positions within Docusign. Docusign reserves the right to change a position's job designation depending on business needs and as permitted by local law.

What you bring

Basic

• 5+ years of experience in machine learning engineering, software engineering, or related operational roles

• Candidates must demonstrate proficiency in Python design patterns, asynchronous programming, and performance optimization

• Proven experience deploying and managing containerized ML services using Kubernetes (k8s)

• Experience in building high-performance, scalable distributed systems that can support large-scale agreement processing and real-time user experience

• An understanding of the full lifecycle is required, specifically managing data ingestion, model training, and production-grade monitoring

• Direct experience building with Large Language Models (LLMs), specifically implementing complex prompt engineering

  • Experience deploying and maintaining ML models in high-traffic, production environments