Software Engineer 1-3 (india)

UiPath UiPath · Enterprise · Bangalore, India · Engineering

Software Engineer to build and scale an AI agentic orchestration platform, focusing on the core orchestration engine that integrates AI agents, robots, and human-in-the-loop workflows for enterprise automation. Requires experience in building production AI systems, multi-agent architectures, orchestration frameworks, and evaluating AI model behavior.

What you'd actually do

  1. Build and Scale: Design, develop, and maintain full stack for Vertical Solutions products leveraging AI Coding Assistants.
  2. Hands-On Development: Write production-quality code daily, leveraging AI tools (Claude, GitHub Copilot, etc.) to enhance your development workflow
  3. Prototype and Ship: Take ideas from Prototype to validate with real customers and turn the ones that prove value into production systems.
  4. Measure what matters: Design evaluations, measure quality against real customer data, and understand when metrics mislead. Our systems are often non-deterministic. Responsible shipping means measuring honestly, not chasing vanity numbers.
  5. Customer-Centric Engineering: Deeply understand who will use the features you build and why they need them, translating customer needs into elegant technical solutions

Skills

Required

  • production AI systems
  • LLMs
  • tool-calling
  • multi-agent architectures
  • orchestration frameworks (LangGraph, LangChain, or equivalent)
  • structured outputs
  • orchestration
  • evaluation of model behavior in real-world workflows
  • distributed systems experience
  • resilient systems with idempotency, replay ability, state management, and long-running jobs
  • analytical thinking
  • rapid prototyping
  • Python
  • C#
  • React
  • TypeScript
  • multithreading
  • asynchronous programming
  • synchronization
  • cloud-native programming models
  • Azure, AWS, or GCP
  • Docker, Kubernetes, or equivalent
  • AI coding tools and coding agents (e.g., GitHub Copilot, Cursor, Claude Code, or similar)
  • object-oriented programming
  • architectural design patterns
  • system design
  • data structures & algorithms
  • agile development
  • CI/CD
  • DevOps
  • infrastructure as code
  • verbal and written communication skills
  • collaboration with globally distributed teams
  • managing complex, time-bound deliverables
  • ability to understand, communicate, and drive complex technical decisions

Nice to have

  • healthcare Tech/ Finance Tech/ Procurement Tech systems experience
  • Data science and evaluation
  • applied ML techniques such as classification, anomaly detection, ranking, or predictive modeling
  • evaluating AI systems using experimentation, metrics, and empirical analysis to improve quality and reliability
  • Data and retrieval systems
  • large-scale data platforms (Snowflake, columnar warehouses, denormalized data models)
  • retrieval-heavy architectures, RAG systems, or citation-grounded AI workflows
  • Engineering for trustworthy AI
  • blending deterministic and probabilistic systems (rules engines + AI)
  • designing eval-driven systems, regression testing for LLM outputs, or human-in-the-loop review workflows
  • Platform and product development
  • Frontend familiarity

What the JD emphasized

  • AI agentic orchestration platform
  • orchestration engine
  • orchestration frameworks
  • orchestration
  • evaluations
  • evaluation of model behavior
  • evaluating AI systems
  • eval-driven systems

Other signals

  • AI agentic orchestration platform
  • orchestrate AI agents, robots, and human-in-the-loop workflows
  • build the core orchestration engine
  • Experience building production AI systems — LLMs, tool-calling, multi-agent architectures, orchestration frameworks
  • Experience with applied ML techniques such as classification, anomaly detection, ranking, or predictive modeling
  • Experience evaluating AI systems using experimentation, metrics, and empirical analysis to improve quality and reliability
  • Experience blending deterministic and probabilistic systems (rules engines + AI)
  • Experience designing eval-driven systems, regression testing for LLM outputs, or human-in-the-loop review workflows