Senior Software Engineer -AI

Could that be you?

About the Role

At UiPath, we're building the next generation of enterprise AI and automation, where intelligent agents, people, and software work together to solve complex business challenges.

We're looking for an exceptional Senior Software Engineer to help build the foundational technologies powering our AI platform. You'll work at the intersection of distributed systems, generative AI, and enterprise software, developing capabilities that enable AI agents and intelligent applications to operate reliably, learn continuously, and deliver meaningful business outcomes at scale.

This is a hands-on engineering role for someone who loves solving difficult technical problems, thrives in ambiguity, and wants to build products that push the boundaries of what's possible with AI.

You'll contribute to critical platform capabilities spanning AI evaluations, agent memory, continuous learning, orchestration, intelligent document processing, and retrieval systems, helping transform emerging AI technologies into reliable, production-ready enterprise solutions.

We're looking for engineers who don't just experiment with AI, but have personally built, shipped, and operated AI-powered products in production.

What You'll Do

• Build next-generation AI capabilities: Design, develop, and scale services supporting AI agents, evaluations, memory, context management, continuous learning, and intelligent document processing.
• Engineer production-grade GenAI systems: Build and operate LLM-powered applications, retrieval-augmented generation (RAG) pipelines, agentic workflows, and document understanding solutions that solve real customer problems.
• Solve complex distributed-systems challenges: Develop highly available, scalable, cloud-native services with strong foundations in asynchronous processing, concurrency, fault tolerance, security, and performance.
• Make AI reliable and measurable: Develop evaluation frameworks, observability, monitoring, and feedback mechanisms that improve AI quality, accuracy, reliability, and performance over time.
• Reflection and Learning: Build systems for continuous learning across multiple modalities, including agents, ontologies, and deterministic logic.
• Own engineering solutions end to end: Take ideas from ambiguous requirements through technical design, implementation, testing, deployment, and ongoing production operations.
• Optimize for enterprise scale: Address challenges involving multi-tenancy, permissions, retries, idempotency, cost efficiency, latency, and system resilience.
• Build across the stack: Contribute to frontend, backend services, APIs, and product-facing experiences, collaborating across technologies to deliver cohesive solutions.
• Partner closely with customers and product teams: Work alongside Product Managers, Forward Deployed Engineers, and other engineering teams to understand customer challenges and translate them into scalable product capabilities.
• Raise the engineering bar: Influence technical decisions, contribute to architecture discussions, mentor fellow engineers, and help establish best practices for building reliable AI-powered software.

What You'll Bring

• Strong professional software engineering experience building, shipping, and operating complex, production-grade applications, ideally within enterprise SaaS or large-scale cloud platforms.
• Deep understanding of distributed systems, backend architecture, microservices, APIs, and cloud-native development.
• Demonstrated hands-on experience building and deploying production GenAI applications, such as LLM-powered products, RAG systems, AI agents, intelligent document processing, or AI-driven enterprise workflows.
• Strong programming skills in Python, C#, or Java, with experience in TypeScript or an interest in developing full-stack capabilities.
• Experience designing systems for scalability, reliability, performance, security, and maintainability.
• Understanding of practical GenAI engineering challenges, including context management, model behavior, retrieval quality, evaluation, latency, and cost optimization.
• Ability to navigate ambiguous technical challenges, make sound architectural decisions, and independently deliver high-quality solutions.
• Strong product instincts and an ability to think beyond individual services or components to understand the end-to-end customer experience.
• Excellent collaboration and communication skills, including the ability to work effectively across engineering, product, and customer-facing teams.

Experience That Will Set You Apart

• Building AI evaluation frameworks, online/offline evaluation pipelines, or feedback-driven improvement systems.
• Experience with agent memory, persistent context, continuous learning, reinforcement learning from human feedback (RLHF), or other AI optimization techniques.
• Developing agentic systems involving orchestration, tool calling, planning, state management, or multi-step execution.
• Deep experience with document intelligence, including OCR, parsing, chunking strategies, embeddings, vector databases, hybrid search, reranking, and grounding.
• Experience improving the reliability and observability of production AI systems, including tracing, quality monitoring, failure analysis, and evaluation-driven development.
• Building enterprise AI platforms, developer infrastructure, search and retrieval systems, or large-scale cloud services.
• Experience collaborating directly with customers to translate complex business requirements into production software.

Why This Role Matters

Enterprise AI is moving beyond experimentation. The next generation of intelligent applications must be reliable, secure, scalable, and capable of improving over time.

At UiPath, you'll help build the engineering foundation that makes this possible.

#LI-MH1

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.