Principal Software Engineer- Agentic AI

UKG; Dadri; On-site; INR 4,000,000 - 6,000,000; Full time

Job summary

UKG is seeking a senior software architect to define and evolve architecture for LLM-powered AI agents across HCM, WFM, HRSD, and Genesis products. The role focuses on agent orchestration, memory, RAG, and secure, scalable enterprise solutions.

You will lead reviews, set standards, and mentor engineers while shaping UKG's broader agentic AI strategy and practices across multiple product lines.

Qualifications

• 10+ years of professional software engineering experience.
• Deep experience designing scalable distributed systems and enterprise platforms.
• Hands-on experience building productionizing LLM-powered applications, AI agents, or other generative AI solutions.
• Strong understanding of agent orchestration, tool calling, RAG, memory, prompt and model versioning.

Responsibilities

• Define and evolve the architecture for LLM-powered AI agents across UKG products.
• Lead architecture and design reviews, setting standards for agent design, code quality, and reliability.
• Provide technical direction and mentorship to engineering teams while aligning with UKG's AI strategy.

Skills

Architectural design

Distributed systems

LLM-powered AI

Agent orchestration

RAG memory patterns

Prompt engineering

Model selection

Mentoring engineers

Security & compliance

Tools

APIs

Vector databases

Knowledge graphs

Cloud-native services

Job description

• Define and evolve the architecture for LLM-powered AI agents, intelligent assistants, and shared agentic capabilities across UKG products, including HCM, WFM, HRSD, and Genesis.
• Drive architectural decisions across agent orchestration, multi-agent workflows, APIs, reusable frameworks, tool and function calling, enterprise data integration, RAG, memory, model selection, and integration patterns.
• Design extensible and reusable agentic capabilities that can be adopted across multiple UKG products while accommodating product-specific requirements and business contexts.
• Ensure AI systems are designed for high availability, scalability, accuracy, security, privacy, observability, auditability, responsible AI, and regulatory compliance.
• Establish robust approaches for AI-agent evaluation, hallucination detection, guardrails, human-in-the-loop controls, prompt and model versioning, and continuous quality improvement.
• Lead architecture and design reviews, setting standards for agent design, code quality, model and response quality, operational readiness, and cross-product adoption.
• Provide technical direction and mentorship to engineering teams while influencing the broader agentic AI strategy and engineering practices across UKG.
• 10+ years of professional software engineering experience
• Deep experience designing and building scalable distributed systems, enterprise platforms, APIs, and cloud- native services.
• Hands- on experience designing, building, and productionizing LLM- powered applications, AI agents, intelligent assistants, or other generative AI solutions.
• Strong understanding of agentic AI concepts and patterns, including agent orchestration, tool and function calling, RAG, memory, prompt engineering, model selection, evaluation, guardrails, and human-in-the-loop workflows.
• Experience integrating AI systems with enterprise applications, APIs, data sources, identity and access controls, and business workflows.
• Experience building and operating secure, observable, resilient, and business- critical AI capabilities consumed across multiple products or engineering teams.
• Understanding of responsible AI practices, including data privacy, security, explainability, auditability, bias mitigation, hallucination management, and regulatory compliance.
• Track record of influencing technical direction across multiple teams or organizations, establishing architectural standards, and driving adoption of shared frameworks and engineering practices.
• Strong problem-solving skills, with the ability to translate ambiguous product or business requirements into clear, extensible technical designs.
• Proven ability to lead highly complex, cross- functional initiatives involving engineering, product management, architecture, AI/ML, data, security, and compliance teams.
• Demonstrated ability to mentor senior engineers, raise engineering standards, and deliver AI capabilities with significant customer and business impact.
• Experience with LLM and agentic AI frameworks, model providers, vector databases, semantic search, knowledge graphs, or enterprise RAG architectures.
• Familiarity with advanced agentic patterns such as multi-agent collaboration, planning and reasoning, dynamic tool selection, agent memory, and autonomous workflow execution.
• Experience designing evaluation frameworks for AI agents, including response quality, task completion, groundedness, hallucination detection, safety, latency, and cost.
• Experience implementing LLMOps or MLOps practices, including prompt and model versioning, experimentation, monitoring, tracing, feedback collection, and continuous improvement.
• Experience designing AI systems with strict requirements for security, responsible AI, compliance, auditability, data privacy, explainability, and tenant isolation.
• Experience integrating conversational or agentic AI experiences with web applications, including Angular-based user interfaces.
• Background in event-driven, workflow-based, service-oriented, batch, or hybrid processing architectures.
• Experience modernizing legacy enterprise applications by introducing AI agents, intelligent automation, or reusable AI platform capabilities.
• Experience leading large-scale technical transformations and successfully moving AI solutions from experimentation to secure, production-grade adoption.