Full Stack Engineer, Applied AI

This is a role posted by Reval Recruiting on behalf of a client

Full Stack Engineer, Applied AI

Location: San Francisco, CA

Workplace: Hybrid

Employment Type: Full-time

Visa Sponsorship: This role offers visa sponsorship.

This role is posted on behalf of the following client: A fast-growing applied AI and operations technology startup helping companies execute physical work across the U.S. without building local teams, leasing warehouses, or managing every on-the-ground detail directly. Its platform coordinates real-world work across 50+ U.S. metros, covering more than 70% of the U.S. population, and grew from zero to multi-millions in gross revenue in 2025.

Role Overview

This client is hiring a Full Stack Engineer, Applied AI to help build the intelligence layer behind a platform that turns customer intent into operational execution. This role focuses on productizing frontier models into reliable production systems, including agent loops, retrieval pipelines, internal tools, evals, observability, and full-stack product workflows. This is not an ML research role or foundation model training role; it is a hands-on engineering position building AI systems that reason through operational context, dispatch work to human operators, detect risk, and take action in the real world.

What You'll Do

• Build full-stack AI product features end to end across React, TypeScript, backend services, database schema, agent logic, and evals.

Searching for Development & Programming roles that provide visa sponsorship? Connect with international employers through Development & Programming Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

• Create agents that receive customer requests and dispatch operational work to the right human operators.
• Build systems that proactively surface operational risks and take action to mitigate them before they become customer-facing issues.
• Design agent loops that can plan multi-step actions, call internal tools, ask for help when needed, and recover when reality changes.
• Build retrieval and structured context systems that ground agents in operational data.
• Create evals, monitoring, and production observability to measure agent quality and catch regressions before users do.
• Improve prompts, tool definitions, model choices, and agent architecture based on real production telemetry.
• Partner directly with design and operations to decide what should be automated, what should be assisted, and what should stay human for now.
• Help define shared AI engineering patterns that future products can build on.

Who You Are

• 2+ years of full-stack engineering experience, with strong product engineering instincts and the ability to own work from UI to backend service to database schema.
• Strong TypeScript experience across frontend and backend, ideally with React, Node, Postgres, and Redis.
• Hands-on experience shipping AI-driven product features in production.
• Working knowledge of LLM APIs, prompting, retrieval, tool use, structured outputs, and evaluation patterns.
• Strong judgment around what should be automated, what should be assisted, and what should remain human-in-the-loop.
• Comfort with messy real-world workflows, noisy inputs, incomplete data, and systems where AI coordinates with human operators.
• Bias toward shipping, learning from production, and iterating quickly.
• Comfort working in an early-stage environment with ambiguity, autonomy, and limited process.
• Interest in building with tools such as OpenAI, Anthropic, custom agent loops, RAG over operational data, in-house evals, Azure, Cursor, Claude Code, and AI-assisted development workflows.

Compensation

Salary: $200,000 - $250,000 per year