Description
Zycus is building a next-generation Agentic AI Platform to autonomously execute enterprise procurement workflows.
We are looking for a deeply hands-on, polyglot engineering leader with a strong foundation in Java/microservices who has evolved into building AI/LLM-driven systems in production.
This role requires someone who can architect, build, and scale intelligent systems end-to-end, while being comfortable working across backend, frontend, and emerging AI technologies.
Roles & Responsibilities
- Architect and build the core Agentic AI platform for Zycus
- Design and implement multi-agent systems (planning, reasoning, execution loops)
- Develop LLM-powered systems integrated with enterprise workflows (ERP, sourcing, contracts)
- Build agent orchestration frameworks (task decomposition, tool usage, memory, feedback loops)
- Develop and scale backend services using Java, Spring Boot, and microservices architecture
- Contribute across the stack including:
- API design and integrations
- Frontend interfaces (React / Angular / Node.js) for AI-driven workflows
- Ensure enterprise-grade reliability:
- Observability, monitoring, debugging AI systems
- Fallback mechanisms and auditability
- Optimize systems for performance, scalability, latency, and cost
- Build reusable platform components and developer frameworks
- Rapidly evaluate and adopt new AI and engineering technologies
- Mentor engineers and drive high engineering standards and best practices
Skills, Experience & Education (Required)
1. Core Software Engineering Expertise
- 10+ years of experience building scalable software systems
- Strong hands-on expertise in:
- Java, Spring Boot
- Microservices and distributed systems architecture
- Proven experience building enterprise SaaS platforms
2. Polyglot & Full-Stack Capability
- Hands-on experience with one or more frontend technologies:
- React / Angular / Node.js
- Ability to work across the stack (backend, APIs, frontend)
- Demonstrated ability to quickly learn and adapt to new technologies
3. AI / LLM Systems Experience (Production-Grade)
- Hands-on experience building:
- LLM-powered applications in production
- Agentic workflows / multi-step AI systems
- Strong understanding of:
- RAG architectures
- Prompting, evaluation, and system design
- Model limitations (hallucination, latency, cost)
4. Agentic AI & System Design
- Experience with or strong understanding of:
- Multi-agent frameworks (LangGraph, AutoGen, CrewAI, or similar)
- Tool-integrated AI systems (APIs, workflows, enterprise systems)
- Memory, orchestration, and feedback mechanisms
- Ability to design end-to-end intelligent systems, not just integrations
5. Hands-On Builder Mindset
- Actively writes production-quality code
- Strong problem-solving and system design capabilities
- Experience owning systems end-to-end (design → build → scale)
6. Enterprise Engineering Rigor
- Experience building systems with:
- High scalability, reliability, and performance
- Observability and debugging frameworks
- Understanding of:
- Security, data privacy, and governance in AI systems
7. Education
- Bachelor’s or Master’s degree in Computer Science / Engineering or related field
- Candidates from top engineering institutes (IITs, NITs, IIITs, or global equivalents) preferred
What This Role Is NOT
- Not a Data Scientist role
- Not a pure research role
- Not a people management-only role
This is a hands-on engineering leadership role for builders who can work across technologies and define the future of enterprise AI systems.