Principal Engineer

About CheckmateCheckmate is building advanced Voice AI systems for some of the largest restaurant brands in the United States, including several in the top ten. Our AI solutions are live today in production with real customers, consistently achieving over 80 percent accuracy. This represents a 1 billion dollar market opportunity, and we are on track to scale to multiple thousand stores in the next 24 months. Join us at this pivotal moment of growth to shape AI products used daily by thousands of staff and customers, bringing together cutting-edge LLM innovation with meaningful real-world business impact. SummaryAs a Principal Engineer in Voice AI will be a leader in the technical direction and execution of Checkmate's next generation agentic Voice AI platform. This role drives the architectural vision, engineering design, and operational rigor behind the systems that power real-time drive-thru automation at scale. As a senior leader, you will partner closely with executive leadership to translate business goals into actionable technical strategies, ensuring the platform's reliability, adaptability, and long-term growth and scalability. You will guide the development of systems that leverage LLMs and Generative AI technologies, oversee the integration of production-grade pipelines, and champion engineering standards that support a rapidly expanding customer footprint. This role requires a hands-on engineering leader, who loves getting their hands dirty in the code, capable of shaping both the technology and the teams responsible for delivering it.Responsibilities Provide directional leadership in the voice ordering system's agentic system design, architecture, and orchestration strategies. Work directly with the VP of Machine Learning, CTO, and CEO to solve and roadmap business critical implementations into the voice application. Build and maintain enterprise-grade Python based systems that integrate LLM and Generative AI frameworks to support Checkmate's end-to-end AI product pipeline. Design CI/CD pipelines for orchestrated LLM driven agentic services and manage deployments across cloud environments that power production drive-thru operations. Own custom model testing, monitoring, and maintenance to ensure reliability throughout the full ML model life cycle. Design prototypes and POCs that demonstrate feasibility, validate approach, and support product direction for the Voice AI platform. Research, design, and train LLM applications aimed at solving real operational challenges inside restaurant environments. Work with internal teams and external partners to provide technical guidance on adopting and integrating LLM capabilities. Requirements Required Qualifications Bachelor's Degree in Statistics, Applied Mathematics, Computer Science, or related technical fields. At least 10 years of hands-on Python experience and 8 years building and maintaining scalable API based services. 5 years working with LLM or GenAI technologies including OpenAI API, ChatGPT, GPT-4, Bard, Synthesia, Pydantic AI, HuggingFace Transformers, PyTorch, or similar. 4 years of agentic process development and iteration life-cycle experience. At least 6 years of experience with AWS, GCP, or Azure, and 6 years of MLOps, CI or CD work, containerization, and deploying models in test and production environments. Strong communication skills with the ability to explain LLM capabilities and limitations to non-technical stakeholders. Desired Qualifications Masters of Science in a relevant field. 13 years of combined professional experience with NLP tools and LLMs. 10 years of experience using NLP tools such as NLTK, CoreNLP, and word or sentence embeddings such as word2vec. Expert in Python, LoRA/QLoRA fine-tuning, classifiers, and ASR's. Deep domain knowledge with an emphasis on tools in NLP or LLM applications.Strong understanding of Responsible AI standards and protocols. Applied research or prototyping experience building LLM driven systems and knowledge of best practices for production LLM development.