Applied AI Engineer (LLM Applications Engineer)

Hygiena provides rapid microbiology diagnostic tests and solutions for mission-critical, time-sensitive processes around the world. Hygiena’s proprietary diagnostic technologies enable customers to; prevent illness and save lives, comply with regulations, protect products and brands, run businesses more effectively. Solutions are sold in a wide range of industries globally, but the core focus is food safety. Headquartered in Camarillo, California and with offices around the world, we are actively looking for talented individuals to help grow the business! At Hygiena we believe: In providing the highest quality products & service Being a leader in innovation Having a compelling desire to improve and win in the marketplace In contributing positively not only in the workplace, but in our community and environment! With rapid growth comes opportunity. We are looking for an Applied AI Engineer (LLM Applications Engineer) to join our team onsite in our Camarillo, CA or Mississauga, Ontario office! This is a full-time / exempt position. Responsibilities: Design, build, and ship production-grade GenAI/LLM applications across Hygiena products including SureTrend — copilots, conversational agents and assistants, workflow automation, and decision support. Implement agentic workflows (tool use, multi-step execution, human-in-the-loop controls) with attention to reliability, safety, and clear failure modes. Design and build advanced retrieval and knowledge systems (RAG): hybrid search, vector and graph stores, indexing strategies, reranking, caching, and source attribution — grounding generation in authoritative sources such as regulatory frameworks (FSMA, HACCP, Codex), validation standards (AOAC, MicroVal, AFNOR), SOPs, and technical documentation. Engineer for production across the full SDLC (build → test → deploy → monitor → iterate). Implement MLOps/GenAIOps practices (CI/CD, reproducibility, environment parity, model/prompt/agent versioning) and build evaluation and observability for GenAI and agentic systems — tracing and instrumentation, regression test suites, automated scoring, and prompt/policy iteration loops. Security-test and red-team LLM and agentic systems — probing for prompt injection, jailbreaks, data/PII leakage, insecure tool use, and unsafe or non-compliant outputs; build adversarial test suites and harden systems and guardrails based on findings. Design for secure deployment with access controls, auditability, sensitive-data handling, and responsible-AI guardrails suited to a regulated domain. Configure and integrate AI solutions into enterprise and customer environments — APIs, data systems, and business applications (e.g., LIMS, QMS, ERP, and collaboration tools) — balancing quality, latency, cost, privacy, and adoption. Support data preparation, transformation, and validation that feeds retrieval, evaluation, and model training/deployment. Collaborate…