AI Agent Systems Software Developer

We’re looking for a contract software developer experienced in building applications and workflows using AI agents — systems that  autonomously perform tasks by reasoning, planning, and executing using LLMs and tools. This role is ideal for someone with strong backend
development skills and hands-on experience working with frameworks like LangChain, AutoGPT, or OpenAI Assistants API.
You’ll be helping us and our clients prototype and deploy intelligent systems that can act, retrieve data, interact with APIs, and adapt dynamically to new tasks. The work is fast-moving, innovative, and ideal for developers who enjoy solving real-world problems with cutting-edge
AI.

Responsibilities:

• Design, build, and deploy AI agent workflows using tools like LangChain, OpenAI 
• Assistants, AutoGPT, or custom frameworks
• Integrate LLMs with external APIs, databases, and tools to extend agent capabilities
• Develop and maintain backend infrastructure (e.g., in Python, Node.js, or TypeScript)
• Implement memory, tool use, and action planning in agent systems
• Troubleshoot and fine-tune agent behavior for reliability, safety, and performance
• Collaborate with project managers, product owners, or clients to clarify goals and refine agent workflows 
• Document systems clearly for handoff or further development

Qualifications

• 3+ years of software development experience
• Proven experience working with LLMs (e.g., GPT-4, Claude, Gemini, or open-source models)
• Experience with agent frameworks such as LangChain, CrewAI, AutoGPT, BabyAGI, etc.
• Strong Python skills (other languages like JavaScript/TypeScript are a plus)
• Familiarity with prompt engineering and chain-of-thought or tool-use strategies
• Comfortable working independently and communicating in client-facing projects

Nice to Have

• Experience with vector databases (Pinecone, Weaviate, FAISS)
• Knowledge of retrieval-augmented generation (RAG) pipelines
• Familiarity with frontend frameworks (React, Vue) for UI development
• Understanding of AI safety, ethical considerations, or prompt alignment