2 months ago
Bengaluru, IndiaSenior
Responsibilities
- Design and implement knowledge graphs and schemas representing agreements, addenda, amendments, and related entities as nodes and edges.
- Build LLM Wiki compilation pipelines that convert ingested agreements into structured, interconnected markdown or graph-based knowledge bases.
- Develop and productionize retrieval architectures for multi-step question answering and navigation across corporate hierarchies.
- Architect and implement Iris’s long-term memory layer, including storage, retrieval, and summarization of chat history, user actions, and administrative overrides.
- Create ML and LLM components combining contract-centric retrieval with institutional memory to adapt to prior decisions, exemptions, and corrections.
- Own end-to-end model and system development, including feature and schema design, training, evaluation, deployment, monitoring, reliability, safety, and debuggability.
Requirements
- 8+ years of professional experience in Machine Learning Engineering or Data Science, with a strong software engineering background.
- Experience with PyTorch or TensorFlow for time series analysis, forecasting or anomaly detection, and NLP.
- Experience building LLM applications using RAG pipelines, LangChain, and vector databases for technical domains.
- Experience with distributed data processing and streaming technologies including Apache Spark, Kafka, and Flink.
- Experience with Python, C++, or Go; CI/CD for ML; and deploying models through APIs using FastAPI or Triton Inference Server.
- Experience building or consuming RESTful and gRPC web services.
- Experience deploying to cloud environments using Kubernetes or Docker containers.
- Experience designing and scaling full-stack or distributed backend systems.
- Preferred experience with Elasticsearch, microservice architecture, highly available scalable services on Azure, and the full software development lifecycle including Git, build processes, testing, and code release.
Benefits
- Hybrid work arrangement requiring access to an office and a minimum of two days per week in-office, with frequency subject to team needs.
- Docusign provides reasonable accommodations for qualified individuals with disabilities or religious needs during the application process.
Tech Stack
Apache FlinkApache KafkaApache SparkAzureC++DockerElasticsearchFastAPIGitGogRPCKubernetesPythonPyTorchTensorFlow
Categories
About DocuSign
DocuSign builds e-signature, contract lifecycle management, and agreement workflow software used by businesses to prepare, sign, and manage contracts. It sells cloud-based subscriptions and APIs that integrate with systems like Salesforce, Microsoft, and Google to automate document workflows and compliance. Founded in 2003 and headquartered in San Francisco, DocuSign is a public company on NASDAQ with over 1.5 million customers in more than 180 countries.