Description

You will design, build, and iterate agentic systems focusing on multi-agent orchestration, autonomous decision-making, planning, and recursive reasoning.

Responsibilities

• Develop and maintain core agent architecture, including loops, memory, planning, and reasoning modules.
• Integrate agents with LLMs, APIs, external tools, knowledge graphs, and data systems.
• Design fallback, recovery, and correction strategies for agents operating in real-world environments.
• Prototype and test agent behaviors, chains, hierarchies, and multi-agent interactions.
• Benchmark and iterate agent performance under latency, cost, and reliability constraints.

Required Skills

• Master’s or PhD in CS, AI, Robotics, or a related field.
• 5+ years in machine learning or agentic AI.
• Strong software engineering background in Python, System Design, and APIs.
• Experience integrating large language models, chain-of-thought, and tool use.
• Familiarity with agentic workflows, reinforcement learning, or meta-learning.
• Knowledge of evaluation metrics for agents (success rate, regret, exploration vs exploitation).
• Experience building production systems, including error handling and scaling.
• Proficiency with LangChain.

Key Skills

Education

Any Graduate