Job Description: We are looking for an Agentic AI Engineer to design, build, execute, test, and orchestrate autonomous AI agent systems that operate across complex, multi-step workflows. You will work at the intersection of large language models, tool-use frameworks, and enterprise data pipelines to deliver reliable, production-grade agentic solutions.
- Qualifications: Minimum 4 years of AI engineering experience, with at least 3 years focused on LLM/agent systems in production.
- Hands-on experience designing agentic architectures: ReAct, plan-and-execute, reflection loops, tool-use patterns.
- Proficiency in Python; experience with at least one agent framework (LangChain/LangGraph, AutoGen, CrewAI, Semantic Kernel, or equivalent).
- Strong understanding of prompt engineering, context window management, and structured output extraction.
- Experience building and testing tool-use integrations: REST APIs, code interpreters, vector databases, SQL executors.
- Familiarity with evaluation frameworks for LLM outputs (RAGAS, custom eval harnesses, LLM-as-judge patterns).
- Understanding of agent safety concerns: prompt injection, tool misuse, hallucination detection, and mitigation strategies.
- Experience with cloud infrastructure (AWS/GCP/Azure) and containerization (Docker, Kubernetes).
- Experience with MLOps, AIOps tooling (MLflow, Weights & Biases, experiment tracking).
Strong experience designing and building memory and caching layers for agentic AI systems, including conversational memory, semantic retrieval, context optimization, and token cost reduction strategies for scalable production deployments
