Lead AI Engineer /Agentic AI Builder

We are seeking a highly motivated and hands-on AI Engineer /Agentic AI Builder to drive the development, implementation, and optimization of autonomous, agentic AI workflows across our Testing, Inspection, and Certification (TIC) operations. In this role, you will be a core builder—leveraging Large Language Models (LLMs), workflow automation, and modern AI APIs. Design and deploy Agentic AI systems capable of executing complex, multi-step tasks to improve internal efficiency and enhance our standard operating procedures (SOPs). This role is ideal for a builder who loves setting up autonomous AI agents, connecting them via modern APIs to real-world business tools, and deploying systems that drastically reduce manual operational bottlenecks. Key Responsibilities: Agentic AI Setup & Orchestration: Design, build, and deploy single and multi-agent systems that utilize autonomous reasoning, tool-calling (function calling), and memory to complete complex workflows with minimal human supervision. Process Automation & Tool Integration: Identify opportunities to automate manual text- and data-heavy workflows within our testing, lab, and inspection operations (e.g., parsing compliance standards, synthesizing lab results, and auto-generating draft inspection reports). Hands-on Coding & API Deployment: Write, test, and deploy clean production-grade Python code to integrate AI agents with internal data sources and third-party APIs. Evaluation& HITL Integration: Implement Human-in-the-Loop (HITL) review mechanisms into agent workflows to ensure high-stakes data is verified by human experts before final execution. Prompt &Context Engineering: Fine-tune system prompts, establish agent guardrails, and implement robust context management to minimize AI hallucinations and ensure data security. Operational Collaboration: Work closely with laboratory technicians, inspectors, and operations managers to map out their manual SOPs and translate them into automated agent workflows. User Adoption & Enablement: Help drive the adoption of new AI tools by creating simple documentation, gathering feedback from end-users, and measuring how much time the tools save. Qualifications: Minimum Requirements: Bachelor’s degree in Computer Science, Data Science, Engineering, or a related technical discipline (or equivalent practical experience/portfolio of built AI projects). Experience: at least 5 years of hands-on experience in software engineering, python programming, or AI prototype development. Agentic AI& LLM Familiarity: Practical experience setting up AI tools, writing effective system prompts, and utilizing LLM APIs (OpenAI, Anthropic, etc.) for tool-calling or multi-step execution. Programming Skills: Strong fundamental programming skills in Python, with experience using collaborative software workflows (e.g., Git). Problem-Solving Mindset: Ability to break down complex, manual human procedures into clear logical rules and steps that an AI agent can execute. Preferred (not required but would be an advantage to have): Agentic Frameworks: Hands-on experience with modern agent orchestration frameworks or graph-based tools (e.g., LangGraph, CrewAI, AutoGen, or flow builders like Flowise/Langflow). Information Retrieval: Exposure to Retrieval-Augmented Generation (RAG) architectures and vector databases. Document Processing: Experience using OCR and AI tools to convert unstructured laboratory PDFs, images, and inspection logs into structured data for agent ingestion. TIC Industry Exposure: A basic understanding of or interest in lab workflows, ISO standards, or regulatory compliance