AI Engineer

Zycus is a global leader in AI-powered Source-to-Pay (S2P) solutions, serving Fortune 1000 enterprises globally. Recognized by leading analysts including Gartner, Forrester, and IDC, Zycus is known for product innovation and AI-led transformation in procurement technology.

AI is not an add-on at Zycus — it is foundational to our product strategy.

We are building next-generation Agentic AI systems that can autonomously reason, plan, and execute across complex enterprise procurement workflows.

We are looking for a AI Engineer to help design and scale enterprise-grade LLM and Agentic AI systems embedded into our SaaS platform.

This role will shape how autonomous AI systems are built, governed, and deployed for Fortune 1000 enterprises. Depending on experience and capability, the role may involve deep hands-on architecture, technical leadership, or leading a focused AI engineering team. We are open to exceptional talent across profiles — from hands-on GenAI architects to AI technical leaders.

In this role, you will define and lead the architecture for Large Language Model (LLM) powered and Agentic AI systems embedded into our enterprise SaaS platform.

You will design scalable, secure, enterprise-grade GenAI systems that:

• Operate autonomously within defined guardrails
• Interact with enterprise data securely
• Orchestrate multi-step workflows
• Deliver measurable business outcomes for Fortune 1000 procurement teams

This role requires deep expertise in LLMs, AI architecture, distributed systems, and enterprise security.

• Design multi-agent orchestration frameworks
• Build memory systems, context handling, and reasoning pipelines
• Architect secure enterprise LLM deployment models (multi-tenant SaaS)
• Define guardrails, validation layers, and human-in-the-loop systems
• Design scalable LLM-based services within a multi-tenant SaaS architecture
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines
• Architect agentic workflows including planning, memory, reasoning, and tool orchestration
• Architect scalable AI services integrated into cloud-native SaaS
• Build prompt engineering standards and evaluation frameworks
• Implement model fine-tuning and domain adaptation strategies

• Integrate GenAI into core S2P workflows (Sourcing, Procurement, Contracts, AP)
• Optimize latency, reliability, and cost efficiency
• Define performance benchmarks and evaluation frameworks
• Build reusable AI services and architecture components

• Ensure data isolation and tenant-level security
• Architect explainability, observability, and traceability frameworks
• Design AI governance and risk management standards
• Align with enterprise compliance requirements