Role Overview
We are looking for an Agentic AI Developer to design, build, and deploy intelligent, autonomous AI systems capable of reasoning, planning, and executing complex tasks with minimal human intervention. This role focuses on leveraging large language models (LLMs) and multi-agent architectures to create scalable, real-world AI applications.
Key Responsibilities
- Design and develop agent-based AI systems that can autonomously perform multi-step tasks
- Build and optimize workflows using large language models (LLMs)
- Implement prompt engineering strategies to improve model accuracy, reliability, and efficiency
- Develop and manage multi-agent orchestration frameworks for complex task execution
- Integrate AI systems into production environments and real-world applications
- Collaborate with cross-functional teams to identify use cases and translate them into AI-driven solutions
- Monitor, evaluate, and improve system performance, scalability, and robustness
- Stay up to date with emerging trends in agentic AI, LLM tooling, and orchestration frameworks
Required Qualifications
- Strong proficiency in Python and experience building production-grade applications
- Solid understanding of LLMs and their capabilities, limitations, and optimization techniques
- Experience with prompt engineering and evaluation methods
- Hands-on experience building or working with autonomous agents or agent frameworks
- Familiarity with APIs, microservices architecture, and cloud environments
- Strong problem-solving skills and ability to design scalable systems
Preferred Qualifications
- Experience with Model Context Protocol (MCP) or similar standards
- Experience with multi-agent orchestration frameworks (e.g., LangGraph, AutoGen, CrewAI, or similar)
- Knowledge of vector databases, embeddings, and retrieval-augmented generation (RAG)
- Experience integrating AI into real-world products or enterprise systems
- Familiarity with MLOps practices, monitoring, and evaluation pipelines
- Understanding of security, safety, and ethical considerations in AI systems
Nice to Have
- Experience with frontend frameworks for AI applications (e.g., building user-facing AI tools)
- Exposure to distributed systems or event-driven architectures
- Contributions to open-source AI/ML projects
What Success Looks Like
- Delivery of robust, scalable agentic AI systems in production
- Measurable improvements in automation, efficiency, or user experience through AI solutions
- Reliable orchestration of multi-agent workflows with minimal supervision
Why Join Us
- Work on cutting-edge AI systems shaping the future of automation
- Opportunity to experiment with emerging technologies and frameworks
- Collaborative, fast-moving environment focused on innovation and impact
