> Markdown version of [/jobs/ext/4774440-principal-engineer-nlp-and-agentic-ai](https://www.wearedevelopers.com/jobs/ext/4774440-principal-engineer-nlp-and-agentic-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Principal Engineer, NLP and Agentic AI - **Company:** Edwards Ltd - **Location:** Irvine, CA, United States - **Experience:** Expert - **Salary:** $157,000 - $223,000 - **Contract:** Permanent contract - **Skills:** AI Evaluation, Artificial Intelligence, Information Retrieval, Language Modeling, Large Language Models, Prompt Engineering, Agentic-AI - **Published:** November 18, 2026 - **Apply:** https://dejobs.org/x/x/5284415C86A44D8EBC9E88AD3C2336CF/job/ ## About the Role * Bachelor's Degree in related field plus 8 years of experience in NLP or LLM engineering with a track record of shipping language-model systems that a downstream team adopted or equivalent work experience based on Edwards criteria -or- Master's Degree plus 6 years of experience or equivalent work experience based on Edwards criteria * Direct experience with agentic system design, including failure modes specific to multi-step agent behavior What else we look for (Preferred): * 10 years in NLP or LLM engineering, with a track record of shipping language-model systems that a downstream team adopted * Building and shipping grounded language-model, retrieval, and agentic systems into production, including vector retrieval, orchestration, security, observability, and lifecycle operations, independent of any single framework * Prompt engineering, fine-tuning, and retrieval-grounding evaluation * Agent trajectory design and reliability evaluation * Experience in a regulated or evidence-sensitive domain where hallucination or grounding failures carry real consequence * Experience building retrieval or agentic systems over enterprise document corpora specifically * Adhere to all company rules and requirements (e.g., pandemic protocols, Environmental Health & Safety rules) and take adequate control measures in preventing injuries to themselves and others as well as to the protection of environment and prevention of pollution under their span of influence/control ## Description * Build and improve domain-adapted language models and retrieval-augmented systems supporting clinical, regulatory, and enterprise document automation * Design and validate agentic workflows, including agent trajectory reliability and failure-mode analysis * Partner with Clinical Operations & Regulatory AI and Enterprise Functions AI to ship models into their document generation, retrieval, and workflow-triage patterns * Work with AI Evaluation to ensure retrieval grounding and agent behavior meet defined shipping thresholds * Other incidental duties