AI Engineer; Prompt

TEGNA Inc. (NYSE: TGNA) helps people thrive in their local communities by providing the trusted local news and services that matter most. With 64 television stations in 51 U.S. markets, TEGNA reaches more than 100 million people monthly across the web, mobile apps, streaming, and linear television. Together, we are building a sustainable future for local news.

We’re hiring a versatile Prompt Engineer and AI builder to design, prototype, and ship rapid AI Solutions that power a modern media business spanning linear TV, digital, web, social, streaming, and apps. You’ll craft AI‑driven tools that help creators find and shape stories, generate scripts and digital narratives, create thumbnails and intro videos, and build agents for accelerating sales and viewership.

You thrive in ambiguity, think end‑to‑end, and bring fresh ideas that translate into working products.

• Build end‑to‑end AI Solutions: clarify the problem, design the approach, write the prompts and prototype quickly
• Create content intelligence workflows: discovery, ideation, outlining, script generation, narrative structuring, and quality review loops.
• Develop creative production assistants: prompts and pipelines for images, video intros, thumbnails, sound and music, and multimodal storytelling.
• Launch conversational and voice agents: design dialog flows, safety/guardrails, escalation logic, and measurable outcomes
• Implement retrieval‑augmented workflows: grounding, chunking, indexing strategies, response synthesis, and guardrails for factuality and tone.
• Orchestrate multi‑step agents: task decomposition, tool‑use design, memory and context strategies, and failure/retry logic for reliability.
• Operationalize prompt systems: reusable prompt patterns, role/task separation, evaluation harnesses, and continuous refinement.
• Ship scrappy, lovable MVPs: wireframe to clickable demo, auth and basic data flows, and deploy to a shareable environment for stakeholders.
• Collaborate cross‑functionally: partner with content, product, audience, growth, and sales teams to prioritize high‑ROI problems and validate solutions.
• Document decisions: assumptions, risks, test plans, and clear instructions so others can run, test, and extend your prototypes.

• Prompt craft and instruction design:
  Few‑shot and chain‑of‑thought strategies; role/task separation; system/content style control.
• Hallucination minimization, grounding, and controlled creativity for different media formats. Evaluation frameworks for prompt quality, including precision/recall of facts and style adherence.
• Retrieval and knowledge workflows:
  Content chunking strategies, context packing, query reformulation, re‑ranking, and synthesis patterns. Guardrails for freshness, safety, and policy alignment; transparent citations and source tracing.
• Agentic design:
  Task planning, tool selection heuristics, state/memory design, interruption and recovery, and outcome verification. Cost, latency, and reliability trade‑offs; clear stop conditions and escalation paths.
• Generative media techniques:
  Story and script structuring, beat sheets, shot lists, and pacing; image and video prompt composition; audio/speech style guides. Consistency controls across modalities (voice, visual style, tone).
• Evaluation and measurement:
  Human+AI evaluation loops, rubric‑based scoring, golden sets, red‑teaming, and regression checks for updates. Business‑focused metrics: time saved, quality lift, conversion/engagement impact, containment for voice agents.
• Product thinking and delivery:
  Rapid prototyping mindset, bias for action, and crisp scoping. Clear UX flows for creators and internal operators; pragmatic guardrails and safety‑by‑design.
• Communication and influence:
  Translate complex AI behavior into simple narratives and demos. Gather feedback from non‑technical stakeholders and close the loop with measurable improvements.

• About 5 years building AI‑powered products or prototypes with hands‑on ownership from concept to demo.
• Demonstrated excellence in prompt writing across text, image, audio, and multimodal use cases.
  
  Strong grasp of retrieval‑augmented generation, agentic…