Sr. AI Engineer

Surround Sound News; United States; Remote; USD 180,000 - 250,000; Full time

Job summary

SurroundSound seeks a Sr. AI Engineer to build the agent systems powering a local-news network. Work with the CTO on architecture, research and drafting flows, and tool orchestration to deliver reliable, sourced drafts for producers.

You will ship production-grade AI tooling, evaluate outputs, and ensure robust retrieval, context handling, and state management while keeping latency and cost in mind. This is a remote US role with full-time commitments.

Qualifications

• Experience shipping an LLM or agent application used by real users.
• Strong backend engineering fundamentals: Python, SQL, APIs, and background jobs.
• Practical experience with model/tool integration, structured outputs, retrieval and workflow state.
• Sound judgment about AI outputs and evaluating changes before release.
• Clear communication and independent problem-solving with AI tools.

Responsibilities

• Design agent workflows: retain reporting context across runs and coordinate research, drafting, and review.
• Evaluations: turn producer corrections into evaluation cases and tests for prompts and retrieval.
• Ship: handle duplicates and failures while measuring quality, latency and cost.

Skills

Python

SQL

APIs

Background jobs

Model integration

Retrieval

Context management

AI tooling

Communication

Tools

AWS

FastAPI

Celery

PostgreSQL

TypeScript/React

Job description

Engineering · Remote, US · Full-time# Sr. AI EngineerBuild the agent systems behind a working local-news network.Apply by emailAll open roles## The roleSurroundSound builds and operates AI-powered local news outlets covering local government, schools, business, and sports. Our agents research and draft stories, and human producers review and publish them. We're backed by a prominent Silicon Valley VC and already generating revenue.## Your first challengeThis full-time position reports to the CTO.Your first challenge: recurring commissions and syndication. Turn a recurring reporting assignment into a reliable agent workflow that retains prior context, gathers evidence, adapts coverage to relevant communities, and delivers sourced drafts for producer review.You'll work on context and retrieval, tool orchestration, durable state, source provenance, and evaluations. Work directly with the CTO to shape the architecture, own delivery, and learn from the producers using what you ship. The goal is useful local coverage with less repetitive work for the newsroom.## What you'll do* Design agent workflows: retain reporting context across runs and coordinate research, drafting, and review.* Evaluations: turn producer corrections and failure traces into evaluation cases and tested changes to prompts, retrieval and tools.* Ship: handle duplicate work, interrupted runs and external-service failures while measuring quality, latency and cost.## What you'll bring* Experience shipping an LLM or agent application used by real users. Internal tools, small products and startup work count. Be ready to explain your contribution, how people used it, and what you improved after launch.* Strong backend engineering fundamentals: Python, SQL, APIs, and background jobs. You can debug and maintain production software.* Practical experience with model/tool integration, structured outputs, retrieval, context and workflow state.* Sound judgment about AI output: checking evidence, recognizing unsupported claims and evaluating changes before release.* Clear communication, independent problem-solving and effective use of AI coding tools. You can explain, review, and validate the code you ship.## Nice to have* Media, publishing or other products where information accuracy matters.* Search, entity resolution, document extraction or long-running workflows.* AWS, FastAPI, Celery, PostgreSQL, or enough TypeScript/React to contribute to producer tools.These foundations can later support national-to-local coverage and local-story discovery, giving you room to expand ownership as the systems mature.## How to applySend your résumé and a brief example of an AI application you've shipped: who used it, what you owned, and a failure you fixed (links to working products or code are welcome) to [e-mail]. Tell us why this role. We read everything.