AI Engineer

Overview

An AI Engineer role (Agent Systems) to design and deploy production-grade agentic AI systems that power intelligent security workflows.

What you'll do

• Design, build, evaluate, and deploy autonomous AI agents and multi-agent systems for security detection and response.
• Develop cost-efficient agentic pipelines optimized for latency, accuracy, stability, and tool-use fidelity.
• Create orchestration frameworks for LLM-based agents with tool use, memory, planning, and multi-step reasoning.
• Experiment with agent techniques such as ReAct, structured output, RAG, and agentic memory architectures.
• Measure and optimize agent performance metrics like task success rate, cost-per-run, and reliability.
• Monitor production agents and improve robustness, observability, and failure recovery.

What you'll need

• 2+ years of experience in AI Engineering, Applied AI, or ML Engineering.
• Strong experience building and deploying agentic AI systems or LLM-powered applications in production.
• Experience designing multi-step, tool-using agents using frameworks such as LangGraph, AutoGen, or CrewAI.
• Strong Python engineering skills.
• Experience working with LLM APIs including OpenAI, Anthropic, and Gemini and open-source models via Hugging Face.
• Experience implementing RAG pipelines, vector stores, and semantic retrieval systems (e.g., FAISS, Weaviate, Pinecone, pgvector).

Details

• Location cities listed: Hyderabad, India; Athens, Greece; Sunnyvale, CA, USA.