AI Agent Engineer

Key Responsibilities:

• Design and implement autonomous AI agents using large language models (LLMs) and reasoning frameworks.
• Build tool-use and planning systems that enable agents to take multi-step actions (e.g., use APIs, browse data, execute code).
• Develop memory, reflection, and goal-tracking mechanisms for persistent agents.
• Integrate LLMs with backend systems, databases, and external APIs.
• Optimize inference performance, safety, and reliability of deployed agents.
• Contribute to multi-agent frameworks (e.g., cooperative or competitive agents).
• Work with research teams to experiment with reasoning, RAG (retrieval-augmented generation), and self-improvement loops.
• Write clean, scalable code and maintain testable agent pipelines.

Skills and Qualifications:

• Bachelors or Masters degree in Computer Science, AI, or related field (or equivalent experience).
• Strong proficiency in Python and experience with LLM frameworks(LangChain, LlamaIndex, OpenAI API, CrewAI, etc.).
• Experience with vector databases (Pinecone, Weaviate, FAISS, etc.) for retrieval and memory.
• Familiarity with prompt engineering, function calling, and tool orchestration.
• Knowledge of reinforcement learning, planning, or multi-agent systems a plus.
• Strong understanding of software engineering principles and API design.
• Experience deploying models using cloud infrastructure (AWS, GCP, Azure, or local inference).
• Excellent problem-solving, collaboration, and communication skills.