Gen AI Engineer

About Zycus

Zycus stands as a global leader in AI-powered Source-to-Pay (S2P) solutions, serving Fortune 1000 enterprises worldwide. Our commitment to product innovation and AI-led transformation in procurement technology is consistently acknowledged by leading industry analysts, including Gartner, Forrester, and IDC.

At Zycus, AI is not an afterthought; it forms the bedrock of our product strategy. We are at the forefront of developing next-generation Agentic AI systems capable of autonomous reasoning, planning, and execution across complex enterprise procurement workflows.

Role Overview

We are seeking a talented GenAI Engineer to contribute to the design and scaling of enterprise-grade LLM and Agentic AI systems integrated into our SaaS platform. This role will play a pivotal part in defining how autonomous AI systems are constructed, governed, and deployed for Fortune 1000 enterprises. Depending on your experience and capabilities, you may undertake deep hands-on architecture, provide technical leadership, or lead a dedicated AI engineering team. We welcome exceptional talent across various profiles, from hands-on GenAI architects to experienced AI technical leaders.

In this capacity, you will be responsible for defining and leading the architecture for Large Language Model (LLM) powered and Agentic AI systems embedded within our enterprise SaaS platform.

Key Responsibilities & Objectives

Design Scalable, Secure, Enterprise-Grade GenAI Systems that:

• Operate autonomously within defined operational guardrails.
• Interact securely with sensitive enterprise data.
• Orchestrate complex, multi-step workflows.
• Deliver tangible business outcomes for Fortune 1000 procurement teams.

This role demands profound expertise in LLMs, AI architecture, distributed systems, and enterprise security principles.

Core Responsibilities

Build Zycus Enterprise-Grade AgenticAI Product

• Design sophisticated multi-agent orchestration frameworks.
• Develop robust memory systems, context handling mechanisms, and reasoning pipelines.
• Architect secure deployment models for enterprise LLMs within a multi-tenant SaaS environment.
• Define and implement strict guardrails, validation layers, and human-in-the-loop systems.
• Design highly scalable LLM-based services integral to a multi-tenant SaaS architecture.
• Build and optimize advanced Retrieval-Augmented Generation (RAG) pipelines.
• Architect agentic workflows encompassing planning, memory, reasoning, and tool orchestration.
• Design scalable AI services seamlessly integrated into cloud-native SaaS offerings.
• Establish comprehensive prompt engineering standards and effective evaluation frameworks.
• Implement strategies for model fine-tuning and domain adaptation.

Production Engineering

• Integrate GenAI capabilities into core Source-to-Pay (S2P) workflows, including Sourcing, Procurement, Contracts, and Accounts Payable.
• Optimize for latency, reliability, and cost efficiency in production environments.
• Define critical performance benchmarks and rigorous evaluation frameworks.
• Develop reusable AI services and architectural components to accelerate development.

Enterprise AI Governance & Security

• Ensure strict data isolation and tenant-level security measures.
• Architect frameworks for explainability, observability, and traceability of AI systems.
• Design and implement robust AI governance and risk management standards.
• Ensure alignment with all relevant enterprise compliance requirements.

Job Requirements

Required Qualifications

• Minimum of 2 years of experience in software architecture or AI engineering.
• Strong hands-on expertise in: LLM orchestration frameworks, RAG architectures, Vector databases, Prompt engineering & evaluation, Multi-agent systems.
• Proven experience designing scalable SaaS architectures on major cloud platforms (AWS / Azure / GCP).
• Deep understanding of enterprise data security and compliance regulations.
• Solid experience in system design and distributed systems.
• Proficiency in Python and modern AI development frameworks.

Preferred Qualifications

• Experience in building AI systems specifically for enterprise workflows.
• A background in Procurement, Supply Chain, or ERP systems is advantageous.
• Experience deploying AI solutions in regulated environments.
• Exposure to reinforcement learning or advanced planning systems.
• Experience with fine-tuning foundation models.

What Makes This Role Unique

• You will architect AI solutions utilized by Fortune 1000 enterprises globally.
• You will build production-scale Agentic AI systems, moving beyond prototypes.
• You will significantly influence the AI direction of a globally recognized S2P platform.
• You will help define the future landscape of autonomous procurement systems.

Why Zycus

Enterprise-Scale AI Impact

Your contributions will power mission-critical systems used by Fortune 1000 companies worldwide, impacting global procurement operations.

Real Agentic AI Development

We are focused on building autonomous AI systems deeply embedded within enterprise workflows, not merely conversational copilots.

Production-Grade Complexity

You will tackle challenges involving multi-tenant SaaS environments, high data sensitivity, stringent compliance requirements, and the delivery of measurable business outcomes.

AI-First Strategy

AI is central to our product roadmap and executive vision, providing a clear and compelling strategic direction.

Industry Recognition

Zycus continues to be lauded by Gartner and Forrester for its innovation and robust product offerings in the procurement technology sector.