AI Agent Engineer

AryaXAI is looking for a passionate and capable engineer to lead the development of our Enterprise AI Agent and AI Data Science Agent workstreams. Our mission is to build agentic systems that bring explainability, safety, and scalability to the forefront of enterprise AI.

As an AI Agent Engineer at AryaXAI, youll play a key role in shaping intelligent agents that assist in enterprise decision-making, automate complex data science workflows, and integrate seamlessly into business ecosystems. These agents will serve as collaborators for enterprise teams—leveraging reasoning, tool use, and memory—while staying aligned with our focus on transparent and trustworthy AI.

Were seeking a strong engineering generalist with deep experience in LLMs, agent frameworks, and production-scale systems. You’ve likely prototyped or shipped agent-based systems, pushed the boundaries of what LLMs can do, and are looking for a meaningful opportunity to build the future of responsible AI.

Responsibilities

• Lead the design and development of Enterprise AI Agents and Data Science Agent systems that combine reasoning, tool orchestration, and memory.
• Collaborate with product, research, and infrastructure teams to create scalable agent architectures tailored for enterprise users.
• Build agent capabilities for tasks like automated analysis, reporting, data wrangling, and domain-specific workflows across business verticals.
• Integrate real-time knowledge, enterprise APIs, RAG pipelines, and proprietary tools into agentic workflows.
• Work closely with the alignment and explainability teams to ensure agents remain safe, auditable, and transparent in their reasoning and output.
• Continuously evaluate and incorporate advances in GenAI (e.g., controllability, multi-modal models, memory layers) into the agent stack.
• Help shape the engineering culture at AryaXAI through mentorship, reviews, and innovation.
  
  

• Demonstrated experience building with LLMs and Agentic frameworks (e.g., LangChain, LangFlow, Semantic Kernel, Haystack, ReAct, AutoGPT, etc.).
• Experience with productionizing AI/LLM workflows and integrating them into real-world applications or systems.
• 2+ years of software engineering experience, ideally with some time in early-stage startups or AI-first environments.
• Strong Python skills and solid understanding of full-stack backend architecture (APIs, cloud infra, databases).
• A passion for building ethical, explainable, and high-impact AI products that solve real enterprise problems.
• (Bonus) Experience working on agent toolchains for data science, ML ops, or enterprise analytics.