D

Docusign

Runs electronic signing and agreement workflows

Senior Software Engineer - AI

AI Application Engineering +1Updated on Nov 13
Full-timeSan Francisco, CA, USA

About the Job

Requirements

  • A Bachelor's or Master's degree in Computer Science or a related field is required.
  • At least 6 years of relevant experience with a Master's degree, or at least 8 years with a Bachelor's degree, is required.
  • Experience developing and deploying generative AI-powered applications, including intelligent chatbots, AI copilots, and autonomous agents, is required.
  • Experience with large language models, transformer architectures such as BERT, GPT, and T5, and applications in text generation, summarization, question answering, and code synthesis is required.
  • Experience with retrieval-augmented generation, embedding techniques, knowledge graphs, and fine-tuning or training large language models is required.
  • Experience in natural language processing, prompt engineering, instruction tuning, context-window optimization, advanced tokenization strategies, and using pre-trained large language models through APIs or open-source models is required.
  • Experience with large-language-model orchestration frameworks such as LangChain and LlamaIndex, and agentic or multi-agent orchestration tools such as LangGraph or CrewAI, is required.
  • Experience developing and implementing the Glean interactive search platform is required.
  • Experience with Python and Bash, and frameworks or tools such as React and Streamlit, is required.
  • Experience with coding copilots such as GitHub Copilot or Cursor is required.
  • Experience with vector databases such as FAISS, Pinecone, Weaviate, and Chroma for embedding storage and retrieval is required.
  • Experience with data preprocessing, augmentation, and visualization techniques is required.
  • Experience contributing to generative AI projects from ideation through deployment, iteration, and evaluation of large-language-model performance is required.
  • Experience with containerization and orchestration technologies such as Docker, Kubernetes, and AWS ECS is required.
  • Experience with AWS services including VPC, IAM, MWAA (Managed Workflows for Apache Airflow), and ECS is required.
  • Experience with software development best practices including Git, testing, continuous integration and continuous delivery pipelines, infrastructure as code with Terraform, automation, and MLOps for generative AI is required.

Responsibilities

  • Conduct applied AI research and translate generative AI advancements into production-ready software features.
  • Lead technical feasibility studies and rapid prototyping to provide an engineering foundation for build-versus-buy architectural decisions.
  • Engineer production-grade natural language processing algorithms and information retrieval systems using spaCy, NLTK, and Hugging Face.
  • Design, build, and maintain scalable retrieval-augmented generation architectures connecting foundational large language models to proprietary enterprise databases.
  • Evaluate and apply embedding models, vector databases, and large language models based on cost, latency, security, and performance requirements.
  • Build enterprise-grade conversational interfaces and analytical AI tools, including QueryGPT, that interface directly with structured data systems through custom middleware.
  • Design and build autonomous multi-agent frameworks such as CrewAI and LangGraph, and scalable agentic platforms focused on distributed-system architecture and secure execution environments.
  • Develop custom extensions and API-based integrations for large language models, creating AI assistants through backend systems programming.
  • Execute model engineering through supervised fine-tuning and reinforcement learning from human feedback to optimize model weight distribution for scalability and reliability.
  • Develop algorithmic prompt-chaining logic and maintain a centralized, version-controlled prompt library integrated into the continuous integration and continuous delivery pipeline.
  • Architect and develop end-to-end evaluation pipelines for large and small language models, and engineer telemetry to capture performance, quantization efficiency, and fine-tuning convergence metrics.
  • Own technical documentation, code maintainability, and reproducibility of the AI infrastructure, aligning it with engineering excellence standards.
  • Bridge time zones and ensure effective handoffs and decision-making with US counterparts.

Desired Qualifications

  • A commitment to engineering excellence through automation, innovation, and documentation is preferred.
  • One or more certifications in cloud, solution architecture, technical architecture, or generative AI are preferred.
  • Proficiency in cloud platforms such as AWS and Azure is preferred.
  • Collaboration with cross-functional teams including Product, Design, Machine Learning, and Data Engineering is preferred.
  • The ability to explain complex generative AI concepts to technical and non-technical stakeholders is preferred.

About the Company

Docusign

Runs electronic signing and agreement workflows

Docusign runs electronic signing and agreement management software for businesses, letting people approve contracts online and track the steps around each agreement. Its eSignature product routes documents to signers and records who signed, while contract lifecycle tools organize preparation, negotiation, and approvals. The Intelligent Agreement Management platform stores contracts in a searchable repository and uses AI to extract terms and connect agreement data to business workflows. Customers use its web applications or embed signing through APIs, and pay for subscriptions based on users, features, and document allowances. Docusign was founded in 2003 and is headquartered in San Francisco.

Company size
5,001-10,000
Company stage
IPO
Headquarters
San Francisco, CA
Founded
2003

Recently Posted Jobs

Explore more opportunities at Docusign

See more jobs