Summary
✨ AI‑Generated
Build and deploy AI agents powered by modern and open-source LLMs. You will create multi-step reasoning and planning workflows, connect agents to APIs and databases, develop evaluation frameworks, and optimize prompts, memory, retrieval, reliability, and safety.
Highlights
Opportunity to design and deploy advanced AI agents using leading and open-source language models. The role covers reasoning, planning, tool use, evaluation, reliability, safety, memory, retrieval, and integrations with real systems.
Description
This role is part of the Jobright Direct Hiring Network, where top companies like Cresta AI, Plaud, Mercor, OpenArt, and 1,500+ others hire top talent directly through our platform.
This is not a mass job posting.
Only select, high-signal candidates are invited and recommended directly to hiring teams
Hiring Company: Creao AI
One-liner: CREAO is redefining the relationship between people and software by empowering users to create custom, conversational AI applications using natural language.
Salary:
Why Join Us:
Role Responsibilities
• Design, develop, and deploy AI agents using LLMs (e.g., GPT, Claude, open-source models)
• Build multi-step reasoning, planning, and tool-using agent workflows
• Integrate AI agents with internal systems, APIs, databases, and third-party services
• Implement evaluation frameworks to measure agent performance, reliability, and safety
• Optimize prompts, memory systems, retrieval pipelines, and agent architectures
• Collaborate with product, engineering, and design teams to translate real-world problems into AI-driven solutions
• Improve system scalability, latency, and cost efficiency
• Monitor agent behavior in production and continuously iterate based on feedback and data
• Ensure responsible AI practices, including privacy, safety, and bias mitigation
Qualitications
Required
• Strong software engineering skills in Python, TypeScript, or similar
• Experience working with LLMs, AI frameworks, or ML systems
• Understanding of agent architectures, such as: Tool use / function calling, Planning & reasoning, Memory & retrieval (RAG)
• Experience integrating APIs, databases, and distributed systems
• Ability to ship production-ready systems with reliability and observability in mind
Preferred
• Experience with frameworks such as LangChain, LlamaIndex, AutoGen, CrewAI, or similar
• Experience with vector databases (Pinecone, FAISS, Milvus, etc.)
• Knowledge of evaluation methods for generative AI systems
• Experience deploying AI systems on cloud platforms (AWS, GCP, Azure)
• Background in ML, NLP, or autonomous systems
