Architect/Lead AI Engineer (Agentic AI)

Role Overview

We are looking for an AI Architect / Led to lead the development of complex, multi-agent systems. Unlike standard "stateless" chatbots, our goal is to build autonomous digital partners that can perform multi-step research, execute code, and self-correct..

Key Responsibilities

Autonomous System Design: Architect multi-agent workflows using Claude and other LLMs that can decompose tasks and adapt to dynamic environments.

Backend Orchestration: Develop scalable services in Python (using FastAPI or Flask) and Java (Spring Boot) to coordinate agent roles, memory systems, and tool invocations.

Tool Integration: Implement Model Context Protocol (MCP) and function calling to allow agents to interact with external APIs, databases, and enterprise systems.

Prompt Engineering: Create structured reasoning chains (e.g., Chain-of-Thought, ReAct) to steer agent behavior and ensure reliable outputs.

Observability & Safety: Build guardrails for agent behavior and implement tracing to monitor non-deterministic AI systems

• Programming Languages:
• Python: Expert level for AI logic, orchestration, and data handling.
• Java: Strong experience for building enterprise-grade backend services and integrating AI into legacy systems.
• LLM Ecosystem: Deep knowledge of Anthropic's Claude API and toolchains like Claude Code for development workflows.
• Experience: Typically 3+ years in software or AI Architect, with at least 2 year dedicated to agentic systems..