Software Engineer - AI

Docusign; Bengaluru; Hybrid; INR 3,500,000 - 7,000,000; Full time

Job summary

Docusign is seeking a Software Engineer to design, build, and scale intelligent, enterprise-grade software with a focus on agentic AI systems. You will develop AI agents, middleware, and integration frameworks connecting Legal Tech and Docusign platforms with enterprise databases.

Go-to-market involves RAG, vector stores, and distributed systems. You will collaborate with Product, Enterprise Architecture, and Legal Tech stakeholders to ensure code quality, reliability, and security.

Qualifications

• PhD not required; proven GenAI project experience is essential.
• Strong background in NLP, LLMs, RAG and embeddings.
• Experience delivering production AI features end-to-end.

Responsibilities

• Translate GenAI research into production-ready features.
• Lead feasibility studies and rapid prototyping for build vs buy.
• Engineer production NLP and retrieval systems using the listed tools.
• Design scalable RAG architectures and integration with databases.
• Develop AI assistants and autonomous agent frameworks securely.
• Own documentation, testing, CI/CD pipelines and MLOps practices.

Skills

GenAI experience

Python

NLP

LLM architectures

RAG

LangChain / LlamaIndex

Multi-agent orchestration

CI/CD / MLOps

Docker / Kubernetes

AWS ECS / VPC

Education

Bachelor’s or Master’s degree in Computer Science or related field

Tools

SpaCy

NLTK

Hugging Face

FAISS

Pinecone

Weaviate

Chroma

LangChain

Glean

Docker

Job description

Company Overview

Docusign brings agreements to life. Over 1.5 million customers and more than a billion people in over 180 countries use Docusign solutions to accelerate the process of doing business and simplify people’s lives. With intelligent agreement management, Docusign unleashes business‑critical data that is trapped inside of documents. Until now, these were disconnected from business systems of record, costing businesses time, money, and opportunity. Using Docusign’s Intelligent Agreement Management platform, companies can create, commit, and manage agreements with solutions created by the #1 company in e‑signature and contract lifecycle management (CLM).

What you’ll do

We are seeking a Software Engineer to design, build, and scale intelligent, enterprise‑grade software solutions, with a strong focus on agentic AI systems and complex integrations across Legal Technology and Docusign platforms. This role is a hands‑on engineering position requiring deep expertise in software design, distributed systems, APIs, and AI‑enabled architectures. The Software Engineer will develop and operate custom‑built applications, AI agents, middleware services, and integration frameworks that connect core Legal Technology and Docusign platforms with enterprise and external systems. A key aspect of this role is the application of agentic AI patterns, including orchestration, tool‑using agents, Retrieval‑Augmented Generation (RAG), and workflow automation. This role partners closely with Product Management, Enterprise Architecture, and Legal Technology stakeholders but remains fundamentally an engineering role, accountable for code quality, system reliability, scalability, and security.

Responsibilities

• Conduct applied AI research to translate theoretical GenAI advancements into production‑ready software features
• Lead Technical Feasibility Studies and rapid prototyping to provide the engineering foundation for “build vs. buy” architectural decisions
• Engineer Production‑Grade NLP algorithms and information retrieval systems using SpaCy, NLTK, and Hugging Face to drive core product capabilities
• Design, build, and maintain scalable RAG architectures that connect foundational Large Language Models (LLMs) to proprietary enterprise databases
• Evaluate and apply appropriate embedding models, vector databases, and LLMs based on cost, latency, security, and performance requirements
• Build enterprise‑grade conversational interfaces and analytical AI tools (QueryGPT) that interface directly with structured data systems via custom middleware
• Design and Build autonomous multi‑agent frameworks (e.g., CrewAI, LangGraph) and scalable agentic platforms, focusing on distributed system architecture and secure execution environments
• Develop Custom Extensions and API‑based integrations for LLM models, creating sophisticated AI assistants through backend systems programming
• Execute Model Engineering through supervised fine‑tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) 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 CI/CD pipeline
• Architect and Develop end‑to‑end evaluation pipelines for LLMs/SLMs, Engineering complex telemetry to capture performance, quantization efficiency, and fine‑tuning convergence metrics
• Own the technical documentation, code maintainability, and reproducibility of the AI infrastructure, ensuring alignment with engineering excellence standards

Job Designation

Hybrid: Employees divide their time between in‑office and remote work. Access to an office location is required (minimum 2 days per week). Positions are assigned a designation of either In Office, Hybrid or Remote and are specific to the role. Preferred designations are not guaranteed when changing positions.

Required Qualifications

• Bachelor’s or Master’s degree in Computer Science or a related field
• 10+ years of relevant experience with a Master’s degree, or 12+ years with a Bachelor’s degree
• Proven experience in developing and deploying GenAI‑powered applications such as intelligent chatbots, AI copilots, and autonomous agents
• Strong understanding of Large Language Models (LLMs), transformer architectures (e.g., BERT, GPT, T5), and their applications in text generation, summarization, question answering, and code synthesis
• Strong understanding of Retrieval‑Augmented Generation (RAG), embedding techniques, knowledge graphs, and fine‑tuning/training of large language models (LLMs)
• Experience in natural language processing (NLP), prompt engineering, instruction tuning, context window optimization, advanced tokenization strategies, and leveraging pre‑trained LLMs (via APIs or open‑source models)
• Proficiency with LLM orchestration frameworks such as LangChain, LlamaIndex, and agentic/multi‑agent orchestration tools like LangGraph, CrewAI, or similar
• Direct working experience in developing and implementing an interactive search platform Glean
• Proficiency in programming languages such as Python and Bash, as well as frameworks/tools like React and Streamlit. Experience with any copilot tools for coding such as GitHub Copilot or Cursor
• Hands‑on experience with vector databases such as FAISS, Pinecone, Weaviate, and Chroma for embedding storage and retrieval
• Familiarity with data preprocessing, augmentation, and visualization techniques
• Proven track record of contributing to GenAI projects from ideation through deployment, iteration, and evaluation of LLM performance
• Experience working with containerization and orchestration technologies like Docker, Kubernetes, and AWS ECS
• Hands‑on expertise with key AWS services including VPC, IAM, MWAA (Managed Workflows for Apache Airflow), and ECS
• Familiarity with software development best practices including Git, testing, CI/CD pipelines, infrastructure as code (Terraform), automation, and MLOps for GenAI

Preferred Qualifications

• Strong commitment to engineering excellence through automation, innovation, and documentation
• One or more certifications such as Cloud, Solution Architect, Technical Architect, or GenAI‑related certifications
• Proficiency in cloud platforms such as AWS and Azure
• Strong problem‑solving skills and the ability to think creatively
• Strong collaboration skills in cross‑functional teams (Product, Design, ML, Data Engineering)
• Ability to explain complex GenAI concepts to both technical and non‑technical stakeholders