Applied AI Engineer

Workman Labs; Boston, Northern (MA, KY); Hybrid; USD 109,000 - 164,000; Full time

Job summary

Hasbro AI Studio in the United States seeks an Applied AI Engineer to build the intelligence layer that makes characters think, respond, and stay true to themselves, combining canon knowledge with LLM behavior at scale.

The role requires 3+ years shipping production LLM-powered systems, deep prompt engineering skills, and strong Python with AWS. Experience with Voice AI and collaboration with creative teams is important for success.

Qualifications

• 3+ years building and shipping production LLM-powered systems.
• Deep expertise in prompt engineering and system prompt design.
• Proficiency with major LLM APIs; strong Python skills and AWS familiarity.
• Voice AI services familiarity (TTS/STT); clear communication with creative and non-technical collaborators.

Responsibilities

• Design and refine system prompts, character behavior definitions, and guardrails for AI characters.
• Build evaluation frameworks measuring character fidelity, response quality, and safety standards.
• Architect RAG systems grounding character responses in canonical knowledge.
• Partner with creative teams translating character attributes into testable AI requirements.
• Lead prompt versioning, regression testing, and model evaluation practices.
• Integrate with multi-provider LLM APIs (OpenAI, Google Gemini, etc.) and evaluate emerging prompt engineering and agentic design techniques.

Skills

LLM systems

Prompt engineering

Python

AWS

Voice AI

Job description

Hasbro's AI Studio is hiring an Applied AI Engineer to build the intelligence layer that lets iconic characters think, respond, and stay true to themselves — combining canon knowledge with LLM behavior, consistently, safely, and at scale.

$109,200 – $163,800 / yr

Location

—

Seniority

Mid

Compared with 41 other Engineering roles: Common across similar roles Unique to this role

What you'll do

Responsibilities

• Design and refine system prompts, character behavior definitions, and guardrails for AI characters
• Build evaluation frameworks measuring character fidelity, response quality, and safety standards
• Architect RAG systems grounding character responses in canonical knowledge
• Partner with creative teams translating character attributes into testable AI requirements Unique
• Lead prompt versioning, regression testing, and model evaluation practices
• Integrate with multi-provider LLM APIs (OpenAI, Google Gemini, etc.) and evaluate emerging prompt engineering and agentic design techniques

What you'll need

Experience

• 3+ years building and shipping production LLM-powered systems
• Deep expertise in prompt engineering and system prompt design
• Proficiency with major LLM APIs; strong Python skills and AWS familiarity
• Voice AI services familiarity (TTS/STT); clear communication with creative and non-technical collaborators