Multimodal understanding: build vision-language systems that let Descript's agentic editing features reason over the visual and audio content of a project
Evaluation: design the benchmarks and evals that make editorial quality measurable, and that balance quality against cost and latency
Data: build the datasets your work depends on, including synthetic data generation where real examples don't exist at scale
Training: train specialized models from scratch or fine-tune existing foundation models, whichever gets the capability we need
Shipping: take models from prototype to production with the agent and engineering teams
Direction-setting: identify the next research direction that should become a Descript feature, not just a paper. More senior candidates should expect to own this directly; more junior candidates will grow into it
Publishing: take your work to academic venues if you'd like. We support it, but it isn't a requirement of the role
Lead or first author of an accepted publication in a top venue: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, or similar
Played a key role in shipping a production feature with deep learning as a core component
More senior candidates (Senior and Staff) should also bring a track record of owning research direction rather than executing a plan handed to them, and experience mentoring or technically leading other researchers or engineers
Where breadth helps
Direct experience in multimodal understanding is welcome but not required, and we don't require domain-specific expertise in computer vision or speech and audio. Our team spans both, and strong general deep learning ability transfers. We hire against the bar above, and then expect you to grow into the domain. Depth in any of these is a strong signal
Vision-language models and multimodal understanding
Generative modeling for video, audio, or images
Post-training, fine-tuning, and RL on large foundation models
Building evaluation systems for generative or agentic outputs where metrics resist clean definitions
Taking a research idea through to a shipped, production-facing feature