AI Staff Engineer, Full Stack

Salt — United States · Posted ~1 hour ago

Lead Onsite

Skills

Full-Stack Development AI Integration RAG AI Agents Structured Outputs Tool Use Frontend Development Backend Development Data Engineering Model Integration Telemetry AI Evaluation LLM Tool Use Full-Stack Technologies

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

A staff-level full-stack engineering role focused on integrating AI capabilities into production software. You will independently take ambiguous requirements from concept to deployment, owning frontend, backend, data, model integrations, and production telemetry while working with retrieval-augmented generation, agents, structured outputs, and tools.

Highlights

Staff-level ownership of end-to-end AI features, with significant autonomy over ambiguous problems, production deployment, system reliability, and evaluation of AI functionality.

Description

We're Hiring: AI Staff Engineer (Full Stack) Manhattan, NY or Miami, FL The Role We are hiring an engineer to join our New York City or Miami team in a senior staff position. You will be responsible for defining, building, and deploying solutions for local hospitality businesses and their customers. The role focuses on integrating AI across our platform to support logistics and merchant tools. Core Responsibilities End-to-End Delivery: Take ambiguous requirements and independently build, iterate, and ship features.AI Integration: Build product features using retrieval-augmented generation (RAG), agents, structured outputs, and tool usage.Full-Stack Ownership: Manage the frontend, backend, data layers, and model integrations.System Reliability: Set up telemetry and evaluation loops to monitor and test AI functionality in production environments. Requirements Experience: 8+ years of software engineering experience, with 3+ years deploying full-stack applications to production.Technical Stack: Ability to build features from the database to the user interface using a web stack with TypeScript and/or Python.LLM Implementation: Experience writing code directly against LLM APIs (e.g., Anthropic, OpenAI, or open-source models), rather than using no-code automation tools.Portfolio: A public record of side projects, open-source contributions, or shipped products that demonstrate independent development. Preferred Qualifications Engineering experience in local commerce, restaurant technology, marketplaces, or delivery logistics.A history of launching AI applications with user traction or contributing to open-source projects.Experience with production LLM infrastructure, vector databases, and evaluation frameworks. If you think this role is a good fit for you or for someone you know, apply or share this opportunity!