AI Modeling Engineer

Palona's AI agents operate in real restaurant environments: noisy phone lines, varied accents, complex menus, interruptions, incomplete information, strict business rules, and customers who expect an immediate, natural response. Improving these systems requires more than selecting the newest model. It requires disciplined evaluation, high-quality data, modeling judgment, experimentation, and production feedback loops.We are looking for an applied AI Modeling Engineer to improve the intelligence, accuracy, safety, latency, and cost of Palona's voice and multimodal agents. You will own problems across model selection and routing, prompting and context, fine-tuning or post-training when justified, speech and language quality, evaluation methodology, dataset development, and model behavior in production.This is a product-facing modeling role. Research depth matters, but success is measured by improvements that survive contact with production and create better guest, restaurant, and business outcomes. You will work closely with product, full-stack, infrastructure, and customer-facing engineers to move from hypothesis to experiment to reliable deployment.What You'll OwnDevelop modeling and experimentation strategies for high-impact agent problems in voice, language, reasoning, ordering, multilingual behavior, and multimodal understandingBuild rigorous offline and online evaluations that measure task completion, accuracy, safety, latency, cost, conversational quality, and business outcomesCreate and maintain representative datasets from simulations, human annotation, production feedback, and difficult edge cases while protecting sensitive dataEvaluate frontier and open-source models and make clear build, buy, route, prompt, fine-tune, or distill decisionsImprove prompting, context construction, memory, tool-use policies, structured outputs, model routing, and fallback behaviorDesign fine-tuning, preference optimization, distillation, or other post-training work when it offers a measurable advantage over simpler methodsPartner with speech and real-time engineers to improve ASR, TTS, turn-taking, interruption handling, pronunciation, multilingual behavior, and end-to-end latencyDevelop analysis tools that explain model failures, slice performance by scenario, detect regressions, and accelerate iterationShip model changes with production guardrails, staged rollouts, monitoring, rollback paths, and clear quality gatesTranslate new research and model releases into concrete product opportunities and communicate tradeoffs to technical and non-technical partnersRaise scientific and engineering standards through reproducible experiments, thoughtful reviews, and clear documentationRequirements3+ years of industrial experience in relevant technical domainStrong machine learning foundations and hands-on experience developing or evaluating production AI systemsStrong Python skills and experience with modern ML tooling such as PyTorch, JAX, Hugging Face, or equivalent systemsPractical experience with LLMs, speech models, multimodal models, or agentic systemsAbility to design reliable experiments, define useful metrics, analyze noisy results, and avoid optimizing against weak proxiesExperience building datasets, evaluation harnesses, model services, or training and inference pipelinesStrong software engineering judgment; your work is reproducible, tested, observable, and usable by other engineersAbility to connect modeling choices to product constraints including latency, cost, privacy, safety, and user experienceComfort operating in ambiguity and collaborating across research, engineering, product, and customer contextsAI-native working habits and genuine curiosity about new model capabilities and limitationsBenefitsCompetitive Salary and Stock Option PlanMedical, dental, vision, retirement, leave, and disability benefits as applicableFamily LeaveShort Term & Long Term DisabilityPaid time off and company holidaysLearning and development support