Software Engineer, Model Integrations

This is a fully remote position, open to applicants in United States.

📋 Description

• Provide immediate support for new model releases. As major foundation models, video generators, voice models, or open-weight checkpoints become available, artists should be able to utilize them in Griptape Nodes right away. You will create the node and library that facilitate this process.

• Convert model behavior into understandable terms for artists. When a model encounters an issue, while the system identifies the problem, the artist may not understand it. Your role is to bridge that gap — transforming technical jargon like "403: proxy model failed with [800 lines of garbage]" into actionable advice such as "Your reference image needs to be at least 1024px wide and 32-bit; yours is 859px and 24-bit." This includes implementing client-side validation, clear error messages, sensible defaults, and predictable behavior that enhance the user experience from "technically functional" to "truly enjoyable."

• Create the next-generation interface for open-source and local models. Design how Griptape Nodes interacts with self-hosted and on-device models, and develop robust local-model support that enables customers to execute chat, agent loops, and more entirely on their devices, forming the foundation for Griptape Studio and other platform components.

• Remain agile in responding to two sources of feedback. With new models being released almost every week and continuous artist feedback, you will cultivate the ability and systems to quickly translate both into delivered enhancements.

• Integrate AI into our development process. Utilize tools like Claude, Cursor, Griptape Nodes, and other resources to streamline workflows. We anticipate that engineers will be able to deliver results faster and with deeper insights due to AI, rather than in spite of it.

• Uphold high-quality standards. Design, implement, test, and document features that align with actual studio workflows. Conduct thorough code reviews, provide honest estimates, and collaborate with Customer Support when issues arise from user feedback.

⛳️ Requirements

• Proficient in Python, backed by solid engineering practices — type hints, tests, packaging, and dependency management are essential in your code. You should be capable of managing a significant feature from start to finish.

• A degree in computer science is required.

• Demonstrated customer empathy and intuition. You can craft validation, error messages, and defaults that effectively communicate technical realities in a way that artists can understand and act upon — without needing to consult an artist for guidance.

• Familiarity with the contemporary model ecosystem — including foundation models, diffusion, video and audio generators, model hubs (like Hugging Face), and the distinctions between running models locally versus through a hosted API.

• Practical experience with local inference tools — such as Ollama, llama.cpp, vLLM, MLX, transformers, or similar. You have successfully run models on someone's laptop.

• Understanding of generative AI principles — including diffusion models, LLMs and agents, fine-tuning, MCP, evaluation metrics, and prompt engineering. You should possess enough knowledge to troubleshoot workflows when issues arise.

• A history of utilizing AI tools (like Claude, Cursor, Copilot, agent frameworks) to genuinely enhance your efficiency, rather than merely as a novelty.

• Strong written communication skills — producing clear design documentation, informative PR descriptions, and code comments that will benefit your future self.

• Comfort with Windows, Linux, and macOS environments.

• ****Nice to have, eager to learn:****

• Experience in deploying AI/ML integrations within a product setting.

• Familiarity with media and entertainment workflows and formats — such as OpenEXR, USD, ACES, OpenColorIO, and common containers and codecs.

• Contributions to open-source ML or AI tools.

• Knowledge of model quantization, LoRA fine-tuning, or production model evaluation.

• Background in node-based, dataflow, or visual programming environments.

• Experience with DCC tools integration (e.g., Nuke, Maya, Houdini, Blender).

🏝️ Benefits

• Health Savings Account & 401K Plan

• Medical, Dental, and Vision plans

• Bonus scheme

• Anniversary day off

• Passion Days

• Annual personal learning & development time