We are looking for an Agentic AI Engineer to join our growing team to design and develop agentic AI systems that can plan, reason, and act. This includes single- and multi-agent AI systems and orchestration of workflows that involve retrieval augmented generation (RAG), contextual awareness, reasoning, tool calling, and inter-agent communication. This role is ideal for software engineers with AI/ML development experience, and the passion for transforming generative AI models into actionable, goal-driven systems capable of solving complex, real-world business problems.
Key Responsibilities
- Architect and build agentic AI systems that integrate agents with foundational generative AI models, third-party tools and enterprise systems, and APIs, using existing agentic frameworks or custom-built orchestrators.
- Build and maintain retrieval-augmented generation (RAG) and reasoning pipelines to ground agent decisions in reliable, real-world data, and enable persistent and adaptive agent behavior.
- Optimize orchestration and reasoning performance, balancing autonomy, interpretability, and reliability.
- Collaborate with Gen AI and application engineers, ML Ops, and product teams to deploy agentic AI systems in production.
- Monitor and benchmark agent performance and ensure that our AI systems are safe, accurate, trustworthy, and deliver an elegant user experience.
- Document agent architectures, communication flows, guard rails, context engineering, and orchestration logic to ensure reproducibility and clarity.
- Stay current with advances in multi-agent orchestration, RAG, cognitive architectures, and AI safety mechanisms.
- Collaborate with cross-functional teams to deliver complete solutions for our customers.
- Bachelor’s or Master’s degree in Computer Science, AI/ML, Data Science, or related fields with 2+ years of experience in development of agentic AI systems, and preferably, 5+ years of overall experience as a software engineer.
- Proficiency in Python and agentic frameworks such as LangGraph, DSPy, AutoGen, CrewAI, etc.
- Experience with APIs and agent communication protocols such as Model Context Protocol (MCP), Agent Communication Protocol (ACP), and Agent-to-Agent (A2A).
- Experience in prompt design, context engineering, and integrating AI agents with multimodal foundational AI models for reasoning, planning, and dialogue.
- Working knowledge of vector databases and retrieval augmented generation (RAG).
- Understanding of context windows, memory graphs, and long-term reasoning strategies in agentic systems.
- Solid foundation in computer science fundamentals such as data structures, algorithms, programming, design patterns, virtualization, etc., and strong problem-solving skills.
- Having high standards of code quality (clean, well-documented, modular, maintainable, reliable, efficient, secure coding) and automated testing.
- Team player with excellent interpersonal skills and ability to collaborate effectively with remote team members.
- Go-getter attitude and ability to flourish in a fast-paced, startup environment.
- Contributions to open-source agentic AI frameworks or orchestration protocols.
- Microservices and cloud deployments (e.g., AWS, Azure, GCP).
- Safety, guardrails, traceability, and explainability for agentic AI systems.