Sobre este puesto de AI Software Engineer, Product en Palona AI
We are looking for a product-focused AI Software Engineer to turn advances in AI into restaurant products that work reliably in the real world. You will build across customer-facing experiences, backend services, agent workflows, integrations, and evaluation systems. The job begins with a customer or product problem and ends when the solution is operating successfully in production—not when a model call works locally.
You may work on voice ordering, reservations, catering, restaurant operations, client configuration, analytics, or entirely new agent capabilities. You will collaborate directly with product, design, customer-facing teams, and restaurant operators; make fast product and technical tradeoffs; and own the quality of the resulting experience.
Our stack includes Python and FastAPI services, PostgreSQL, TypeScript, React and Next.js applications, real-time voice agents built with LiveKit, cloud infrastructure on AWS, and modern LLM, speech, and multimodal providers. Exact stack match is less important than full-stack range, product judgment, and a record of shipping.
What you’ll own
- Build and ship end-to-end AI product experiences from problem discovery and prototype through launch, measurement, and iteration.
- Develop customer-facing interfaces, backend APIs, data models, agent tools, and integrations as one coherent product.
- Design agent workflows that combine models, context, memory, business rules, deterministic services, and human escalation.
- Work directly with restaurant and internal users to understand failures, uncover unmet needs, and convert feedback into reusable product capabilities.
- Integrate with POS, reservation, messaging, telephony, and other external systems while handling imperfect data and real operational constraints.
- Build evaluations, instrumentation, guardrails, and feedback loops so probabilistic behavior can be measured and improved.
- Improve latency, reliability, accuracy, usability, and cost across the full experience—not only within one layer of the stack.
- Use AI-native development workflows to prototype and deliver quickly while retaining ownership of architecture, tests, security, and correctness.
- Participate in product and technical planning, make tradeoffs explicit, and drive decisions when the path is ambiguous.
- Raise the quality of nearby systems through code review, documentation, design discussion, and pragmatic refactoring.
Requirements
- 3+ years of industrial experience in relevant technical domain.
- Strong software engineering fundamentals and experience shipping production web or platform products.
- Depth in either Python/backend engineering or TypeScript/React frontend engineering, plus the ability and desire to work effectively across the full stack.
- Experience building with LLMs, speech models, computer vision, or agent systems beyond a toy prototype.
- Product judgment: you can simplify scope, identify the highest-leverage user problem, and distinguish an impressive demo from a valuable product.
- Experience designing APIs, data models, asynchronous workflows, and integrations with external systems.
- A strong quality bar for testing, observability, security, reliability, and user experience.
- Comfort working directly with users and operating in a fast-changing startup environment.
- AI-native working habits paired with independent technical judgment.
Benefits
- Competitive Salary and Stock Option Plan.
- Medical, dental, vision, retirement, leave, and disability benefits as applicable.
- Family Leave
- Short Term & Long Term Disability
- Paid time off and company holidays.
- Learning and development support.