Principal Engineer -Intelligent Document & Context Grounding

Principal Engineer · Principal · Full Time

BellevueUSD 200k – 250k2w ago
Apply for this role

Opens UiPath's application page

Role

What you'll do.

Principal Engineer role at UiPath focused on building the AI platform that powers trustworthy enterprise agents through Intelligent Document Processing and Context Grounding. This hands-on engineering leadership position requires 10+ years of large-scale software systems experience with significant production AI expertise, deep distributed systems knowledge, and proficiency in Python and/or C#. You'll design and deliver core services for enterprise document understanding, retrieval, RAG systems, and knowledge grounding while mentoring senior engineers and influencing technical direction across multiple teams.

Responsibilities

  • Design and Build Production AI Systems: Design and deliver core services powering enterprise document understanding, retrieval, knowledge grounding, and Retrieval-Augmented Generation (RAG) across the UiPath platform. Own systems responsible for document ingestion, parsing, extraction, chunking, embedding, indexing, retrieval, knowledge management, evaluation, and answer grounding.
  • Improve Enterprise AI Quality Metrics: Drive continuous improvements in retrieval quality, answer quality, groundedness, attribution, latency, scalability, and cost efficiency. Evaluate emerging AI techniques, challenge architectural assumptions, and introduce innovative approaches as large language model capabilities evolve.
  • Architect Distributed Systems at Scale: Design highly available, multi-tenant cloud services processing enormous volumes of enterprise content while maintaining reliability, security, and performance. Work across distributed services, event-driven architectures, search platforms, vector databases, APIs, orchestration, and cloud-native infrastructure.
  • Lead Through Technical Excellence and Mentorship: Actively shape architectural decisions across organizations, mentor senior engineers, participate in critical design reviews, establish engineering standards, help teams make thoughtful technical tradeoffs, and raise the quality of engineering practices across the organization.
  • Cross-Functional Collaboration: Partner closely with Product Managers, Applied Scientists, Designers, and Engineering Leaders to translate ambiguous AI opportunities into production capabilities that enterprise customers depend on daily.

Qualifications

What we look for.

Technical

  • Production AI Systems Development

    Significant, demonstrated experience shipping production AI products and machine learning systems at scale, including end-to-end responsibility from design through deployment and monitoring.

  • Backend Engineering Expertise

    Strong proficiency in Python and/or C# for building scalable backend systems, microservices, and enterprise applications.

  • Distributed Systems & Cloud Architecture

    Deep understanding of distributed systems design patterns, cloud-native architectures, and multi-tenant platform design. Experience with Azure, AWS, or GCP.

  • Modern Retrieval Systems and RAG

    Strong understanding of Retrieval-Augmented Generation, embeddings, vector search, evaluation frameworks, and LLM-powered applications for enterprise context grounding.

  • Scalable API and Service Design

    Experience building scalable APIs, microservices, event-driven systems, and high-performance distributed services capable of handling enterprise-scale workloads.

  • Document Processing and Knowledge Systems

    Experience with intelligent document processing, OCR, knowledge graphs, knowledge management systems, and extracting structured information from unstructured content.

Education

  • Computer Science or Related Field

    Bachelor's degree in Computer Science, Software Engineering, or equivalent professional experience demonstrating mastery of fundamental software engineering principles.

Experience

  • Large-Scale Software Systems

    10+ years of experience building, architecting, and shipping large-scale software systems in production environments.

  • Technical Leadership and Mentorship

    Proven track record of mentoring senior engineers, influencing technical direction beyond immediate team scope, and establishing engineering standards across organizations.

  • Multi-Tenant Enterprise Platforms

    Experience designing, building, and maintaining reliable, multi-tenant enterprise platforms with high availability, security, and governance requirements.

  • Ambiguous Problem-Solving

    Demonstrated ability to tackle ambiguous technical problems, make thoughtful engineering tradeoffs, and balance long-term architecture with short-term execution.

Skills

Required

  • Python

    Expert-level Python development for building scalable backend services, data processing pipelines, and AI system components.

  • C#

    Strong C# expertise for building enterprise applications, microservices, and cloud-native systems on Azure or other cloud platforms.

  • Distributed Systems Architecture

    Deep knowledge of distributed systems patterns, consensus algorithms, eventual consistency, and designing highly available services.

  • Cloud Platforms

    Proficiency with Azure, AWS, or GCP including containerization, orchestration, managed services, and cloud-native deployment patterns.

  • Retrieval-Augmented Generation (RAG)

    Strong expertise in building and optimizing RAG systems, including retrieval evaluation, answer grounding, and attribution for enterprise AI applications.

  • Vector Search and Embeddings

    Experience with vector databases, semantic search, embedding models, and similarity-based retrieval for knowledge grounding and contextual understanding.

  • Technical Communication

    Excellent ability to explain complex technical concepts clearly to diverse audiences including engineers, product managers, and non-technical stakeholders.

Preferred

  • Azure Cloud Platform

    Nice to have

    Preferred experience with Microsoft Azure services including Azure Cognitive Services, OpenAI integration, and Azure-based AI/ML infrastructure.

  • Kubernetes and Container Orchestration

    Nice to have

    Experience deploying, scaling, and managing containerized applications using Kubernetes, Docker, and related container orchestration technologies.

  • Event-Driven Architecture

    Nice to have

    Knowledge of event-driven design patterns, message queues, event streaming platforms, and asynchronous service communication.

  • Large Language Models and NLP

    Nice to have

    Hands-on experience working with large language models, fine-tuning, prompt engineering, and building applications that leverage LLM capabilities.

  • Knowledge Graphs

    Nice to have

    Experience building or working with knowledge graph systems for organizing enterprise knowledge and enabling semantic reasoning.

  • Search Platform Architecture

    Nice to have

    Familiarity with Elasticsearch, Solr, or other search platforms, including indexing strategies, query optimization, and relevance tuning.

  • Intelligent Document Processing

    Nice to have

    Experience with OCR technologies, document parsing, extraction, and processing for intelligent information retrieval.

  • Evaluation Frameworks for AI

    Nice to have

    Knowledge of building evaluation frameworks for assessing AI model quality, groundedness, attribution, and other enterprise AI metrics.

Tech stack

Languages

PythonC#

Frameworks

FastAPI / Django.NET / ASP.NET CoreCelery / Apache Airflow

Databases

Vector Databases (Pinecone, Weaviate, Milvus)PostgreSQL / Azure SQLElasticsearch / OpenSearchRedis / Azure Cache

Tools

DockerKubernetesAzure DevOps / GitHub ActionsTerraform / Infrastructure as Code

Other

Retrieval-Augmented Generation (RAG)LLM APIs and FrameworksEmbeddings and Semantic SearchOptical Character Recognition (OCR)Knowledge GraphsAI Model Evaluation FrameworksDistributed Systems Patterns

Compensation

Pay and benefits.

Base·USD 200,000 – 250,000

Equity·Stock options

Benefits

  • Flexible Work Arrangements

    Options for hybrid, office-based, or remote work arrangements depending on business needs and team requirements, providing flexibility in when and where work is performed.

  • Enterprise AI Impact

    Opportunity to work on next-generation enterprise AI systems that power trustworthy agents capable of reasoning over business context and delivering measurable outcomes for thousands of organizations.

  • Technical Leadership Opportunity

    Hands-on principal-level role that combines deep technical work with architectural influence, mentorship, and organization-wide technical direction setting.

  • Collaborative Cross-Functional Team

    Work closely with Product Managers, Applied Scientists, Designers, and Engineering Leaders to translate complex AI opportunities into production capabilities.

  • Continuous Learning Environment

    Engage with cutting-edge AI technologies, emerging techniques, and evolving large language model capabilities as part of daily work on production systems.

  • Inclusive and Diverse Workplace

    Work environment that values diverse backgrounds, experiences, and perspectives with commitment to equal opportunities regardless of age, race, color, religion, sex, sexual orientation, gender identity, national origin, disability, neurodiversity, or veteran status.

Process

Interview steps.

  1. 01

    Application and Screening

    Submit your application through the AshbyHQ portal. Qualified candidates will be contacted for an initial screening conversation with a recruiter to discuss background, career trajectory, and alignment with the Principal Engineer role.

  2. 02

    Technical Discussion with Hiring Manager

    Deep-dive conversation with the hiring manager covering your experience shipping production AI systems, distributed systems architecture, and approach to building enterprise-scale document processing platforms.

  3. 03

    System Design Interview

    Technical interview focused on designing large-scale distributed systems, discussing architectural decisions, tradeoffs, scalability considerations, and how you would approach building systems similar to those at UiPath.

  4. 04

    AI/ML and RAG Systems Discussion

    Interview with technical leads covering your expertise in Retrieval-Augmented Generation, embedding systems, vector search, LLM integration, retrieval evaluation, and production machine learning systems.

  5. 05

    Leadership and Mentorship Conversation

    Discussion with senior leaders about your experience mentoring engineers, establishing technical standards, influencing architectural decisions, and your approach to technical leadership at the Principal level.

  6. 06

    Team Collaboration and Product Discussion

    Conversation exploring your ability to collaborate across disciplines, your understanding of product trade-offs, and how you balance short-term execution with long-term architectural vision.

Full posting

Original listing.

Life at UiPath

The people at UiPath believe in the transformative power of automation to change how the world works. We’re committed to creating category-leading enterprise software that unleashes that power.

To make that happen, we need people who are curious, self-propelled, generous, and genuine. People who love being part of a fast-moving, fast-thinking growth company. And people who care—about each other, about UiPath, and about our larger purpose.

Could that be you?

Principal Software Engineer – Intelligent Document Processing & Context Grounding

Build the AI platform that powers trustworthy enterprise agents.

At UiPath, we're building the next generation of enterprise AI—agents that don't just generate responses, but understand business context, reason over enterprise knowledge, and deliver trustworthy outcomes at scale.

As a Principal Software Engineer, you'll help define and build the Intelligent Document Processing and Context Grounding platforms. Your work will enable AI agents to ingest, understand, retrieve, and reason over large volumes of enterprise documents while maintaining accuracy, security, governance, and performance.

This is a hands-on engineering leadership role for someone who has repeatedly shipped production AI systems and enjoys solving some of the hardest infrastructure challenges in enterprise software.

You'll influence technical direction across multiple teams while remaining deeply involved in architecture, implementation, mentoring, and product delivery.

What You'll Do

Build production AI systems

Design and deliver the core services that power enterprise document understanding, retrieval, knowledge grounding, and Retrieval-Augmented Generation (RAG) across the UiPath platform.

You'll own systems responsible for:

  • document ingestion

  • parsing and extraction

  • chunking and embedding

  • indexing

  • retrieval

  • knowledge management

  • evaluation

  • answer grounding

Raise the quality bar for enterprise AI

Drive improvements in:

  • retrieval quality

  • answer quality

  • groundedness

  • attribution

  • latency

  • scalability

  • cost efficiency

You'll evaluate emerging techniques, challenge assumptions, and introduce better architectural approaches as AI capabilities continue to evolve.

Solve difficult distributed systems problems

Architect highly available, multi-tenant cloud services that process enormous volumes of enterprise content while maintaining reliability, security, and performance.

You'll work across:

  • distributed services

  • event-driven architectures

  • search platforms

  • vector databases

  • APIs

  • orchestration

  • cloud-native infrastructure

Lead through technical excellence

Principal Engineers at UiPath don't simply review designs—they actively shape them.

You'll:

  • influence architectural decisions across organizations

  • mentor senior engineers

  • participate in critical design reviews

  • establish engineering standards

  • help teams make thoughtful technical tradeoffs

  • raise the quality of engineering across the organization

Partner across Engineering, Product, and Applied AI

Work closely with Product Managers, Applied Scientists, Designers, and Engineering Leaders to turn ambiguous AI opportunities into production capabilities customers rely on every day.

What We're Looking For

We're looking for builders.

Engineers who enjoy taking complex problems, designing elegant systems, and shipping software that customers depend upon.

Successful candidates will typically have:

  • 10+ years building large-scale software systems

  • Significant experience shipping production AI products

  • Strong backend engineering experience in Python and/or C#

  • Deep understanding of distributed systems and cloud-native architectures

  • Experience building scalable APIs, microservices, and event-driven systems

  • Strong understanding of modern retrieval systems including RAG, embeddings, vector search, evaluation, and LLM-powered applications

  • Experience designing reliable, multi-tenant enterprise platforms

  • Excellent communication skills and the ability to explain complex technical concepts clearly

  • A track record of mentoring engineers and influencing technical direction beyond their immediate team

Technologies You May Work With

Our technology stack continues to evolve, but experience in areas such as the following is valuable:

  • Python

  • C#

  • Azure (preferred), AWS, or GCP

  • Docker

  • Kubernetes

  • Distributed systems

  • Event-driven architectures

  • Search platforms

  • Vector databases

  • LLMs

  • Retrieval-Augmented Generation (RAG)

  • Embeddings

  • OCR

  • Intelligent Document Processing

  • Knowledge Graphs

  • Evaluation frameworks

What Makes Someone Successful Here

The strongest engineers on this team don't simply know AI—they know how to build AI products.

They enjoy:

  • solving ambiguous technical problems

  • making thoughtful engineering tradeoffs

  • shipping production software

  • collaborating across disciplines

  • mentoring other engineers

  • balancing long-term architecture with short-term execution

Most importantly, they remain hands-on.

This is a role for engineers who still love building.

Why Join UiPath?

Enterprise AI is entering its next phase.

Organizations aren't looking for chatbots—they're looking for AI systems that can reason over their knowledge, operate responsibly, and deliver measurable business outcomes.

At UiPath, you'll help build the platform that makes that possible.

If you're excited by difficult engineering problems, modern AI systems, and building software that thousands of organizations rely on every day, we'd love to talk.

#LI-MH1

Maybe you don’t tick all the boxes above—but still think you’d be great for the job? Go ahead, apply anyway. Please. Because we know that experience comes in all shapes and sizes—and passion can’t be learned.

Many of our roles allow for flexibility in when and where work gets done. Depending on the needs of the business and the role, the number of hybrid, office-based, and remote workers will vary from team to team. Applications are assessed on a rolling basis and there is no fixed deadline for this requisition. The application window may change depending on the volume of applications received or may close immediately if a qualified candidate is selected.

We value a range of diverse backgrounds, experiences and ideas. We pride ourselves on our diversity and inclusive workplace that provides equal opportunities to all persons regardless of age, race, color, religion, sex, sexual orientation, gender identity, and expression, national origin, disability, neurodiversity, military and/or veteran status, or any other protected classes. Additionally, UiPath provides reasonable accommodations for candidates on request and respects applicants' privacy rights. To review these and other legal disclosures, visit our privacy policy.

Redirects to UiPath's application page.

Other roles

More at UiPath.

View all 20 roles