Deep Learning Deployment Engineer (Remote)
San Francisco, California /
AI Foundation is looking for a Deep Learning Deployment Engineer to focus on deploying research models to web and mobile clients. You and the Deployment team will be primarily responsible for the deployment loop between research-driven AI models and user devices. You will work with researchers developing deep learning models across multiple disciplines: audio synthesis, natural language processing, and computer vision and then deploying these models to production.
- Own the deployment loop between deep learning models and their use in a browser or mobile device.
- Collaborate and work closely with engineers to translate and deploy new AI/DL solutions and models to a production environment.
- Be the voice in the room that guides development work by ensuring work being done by the team is deployable in an end to end system.
- Ensure model performance remains within expected bounds when promoting experimental models to production
Specific skill sets this candidate will have:
- 1-3+ years of hands-on, real-world experience with Machine Learning / Deep Learning models and their deployment to production.
- 4-8 years of overall software engineering and expertise in several of: Java, Scala, Javascipt, C++, Python, Go and good experience building code in a production environment.
- Experience with deep learning frameworks: PyTorch (preferable), Tensorflow, Keras
- Deep familiarity with ONNX, ONNX.js, Tensorflow.js, Core ML, and other AI ML/DL formats will be absolutely critical.
- Ability to quickly translate research work into high-quality production code with a strong sense of good system design.
- Experience with deploying AI models in constrained environments, including Model Compression techniques such as Quantization, Pruning, Distillation
- Good overall background with various Cloud environments including AWS and Google Cloud.
- Experience developing software for users on Mobile devices (iOS and Android) and browsers.
- Good communication and organization skills, with a logical approach to problem-solving, good time management, and task prioritization skills
The AI Foundation is a foundation for the future, and our working style reflects this. We have a highly talented, multi-disciplined and widely distributed task force, moving fluidly between our offices in San Francisco, Los Angeles, Las Vegas, New York - and home/remote-based spaces.
We are committed to a culture of flexibility, diversity, and fun for all of our employees. We are working on some of the most challenging technical problems and we know the solutions will come from all of us working together in an inclusive, transparent and open manner.
It is our belief that frontier technologies require frontier-type mentalities, a willingness to forge into the unknown.
We want the best minds to come together and work on AI. Does this description fit you? If so, get in touch ASAP.