Get new jobs for this search by email

We are seeking an AI Agent Developer to design, build, and deploy intelligent agents that can operate autonomously within digital environments. This role focuses on the development of AI agents that perform reasoning, planning, decision-making, and interaction tasks using large language models (LLMs), multi-agent systems, or simulation frameworks. You will work at the frontier of AI development, creating agents that learn from data, communicate with users or other systems, and adapt to complex, dynamic environments. Responsibilities: Design and implement AI agents using LLMs, planning algorithms, and decision-making frameworks. Develop agent architectures that support autonomy, interactivity, and task completion. Integrate agents into applications, APIs, or workflows (e. g., chatbots, copilots, automation tools). Collaborate with researchers, engineers, and product teams to iterate on agent capabilities. Optimize agent behavior through feedback loops, reinforcement learning, or user interaction. Monitor performance, conduct evaluations, and implement safety and guardrail mechanisms. Maintain thorough documentation of agent logic, design decisions, and dependencies. Requirements: Strong programming skills in Python (or similar) and experience with AI/ML libraries (e. g., LangChain, OpenAI API, Hugging Face, PyTorch). Understanding of agent-based modeling, multi-agent systems, or reinforcement learning. Experience building applications with LLMs or generative AI models. Familiarity with API development, backend services, and deployment pipelines. Ability to work independently in experimental and fast-paced environments. Bachelor's or Master's degree in Computer Science, AI, Machine Learning, or a related field. Preferred Qualifications: Experience with frameworks for autonomous agents (e. g., AutoGPT, CrewAI, LangGraph, ReAct, BabyAGI). Background in human-AI interaction, conversational UX, or simulation environments. Knowledge of vector databases, prompt engineering, or retrieval-augmented generation (RAG). Contributions to open-source AI projects or a portfolio of agent-based systems. Understanding of the ethical, social, and safety considerations of autonomous AI systems.

#J-18808-Ljbffr