Multi Agentic AI Engineer - RAG/LLM

Title : Multi Agentic AI Engineer

Description :

We are seeking immediate joiners with strong Backend skills with Multi Agent AI Systems.

If this role suits your current expertise, please give me a call to discuss further.

About the Project :

The team is building multi-agent AI systems that power intelligent, autonomous support experiences for millions of customers.

The platform combines LLM reasoning, multi-agent orchestration, RAG, tool calling, workflow automation, backend services, and a hybrid stack including Node.js, Java/Raptor, Muse UI, and Python ingestion pipelines.

The primary focus is building production-grade agents capable of reasoning, taking actions, and resolving customer issues end-to-end.

Short Summary :

- Requires deep agent skills beyond RAG - MCP servers, prompting strategies, context management, tool calling, OpenAI SDKs, and orchestration workflows.

- Must understand agent system design end-to-end and the agentic landscape.

- Primary focus : building production-ready agents for the multi-Agent Workstation.

Must-Have Skills :

Core Engineering :

- Full-stack engineer with strong backend skills, especially in Node.js and Java (Spring Boot or Raptor(React)).

- 6 - 12 years software engineering with strong CS fundamentals, distributed systems, microservices, and API design.

Advanced LLM/AI Engineering :

- Experience building agents, not just RAG or simple LLM calls.

- Strong knowledge of :

1. OpenAI SDKs and libraries

2. LLM prompting strategies

3. Multi-agent orchestration

4. Tool calling / agent tool execution

5. MCP Servers (Model Context Protocol)

6. RAG pipelines and vector retrieval

5. Context management and memory systems

- Ability to design guardrails, fallback logic, and safe automation patterns.

- Experience designing scalable backend systems, orchestration workflows, and session/context storage.

System Level AI/Agent Architecture :

- In depth understanding of what they have built end-to-end: design choices, trade-offs, scaling, and performance.

- Deep awareness of the agentic AI landscape: plannerexecutor models, multi-agent collaboration, grounding techniques, safety frameworks.

- Ability to design full agent systems, not just backend services - workflow logic, planning, tool-calling, memory, context, and safety.

- Understanding of retrieval, reasoning, orchestration, action workflows.

- Ability to evaluate, monitor, and optimize agents in production.

Platform & DevOps :

- Strong understanding of secure coding, privacy, auditability, and production-grade observability.

- Experience with Git, CI/CD, Docker, Kubernetes, and modern DevOps practices