Description

Design and build systems utilizing specialized LLM agents for complex data retrieval, reasoning, and validation.

Responsibilities

• Design and implement Multi-Agent Systems (MAS) using frameworks like the Agent Development Kit (ADK) to solve multi-step reasoning tasks.
• Architect "Human-in-the-Loop" (HITL) workflows, managing hand-offs between agents and human experts.
• Implement advanced reasoning patterns, including Chain-of-Thought (CoT), ReAct, and Self-Reflection, to improve output transparency.
• Optimize long-context window utilization when analyzing vast datasets for agent coherence.
• Establish rigorous AI Evaluation (Eval) frameworks to measure agent performance, including trajectory analysis and faithfulness.

Required Skills

• 6+ years of experience in AI development, preferably on Google Cloud Platform.
• Solid understanding of Python programming.
• Experience building Agents specifically using Google ADK or similar agentic frameworks.
• Familiarity with LLM Tuning techniques (SFT, CoT, ReAct).
• Experience implementing AI evaluation methods/metrics (Precision, Recall, F1 score for trajectories).
• Experience with agentic AI, managing sequential and loop-based workflows.
• Ability to debug and perform Root Cause Analysis (RCA) for agentic issues.
• Experience deploying AI Solutions within an agent-based framework.
• Familiarity with Agile development processes.

Key Skills

Education

Any Gradute