What you could work on
- Architectures for memory: graph representations, retrieval, hierarchical context, long-horizon reasoning over state.
- Training signal from traces: how a structured workflow record becomes data a model can learn from.
- Architectures for continual learning and proactive surfacing.
- Benchmarks. Help shape the evaluations the work gets measured against.
You should have
- Background in some subset of: representation learning, retrieval, graph models, sequence models, RL, LLM post-training, agent systems.
- The taste to tell what's intellectually interesting apart from what's product-useful.
- The habit of reasoning from first principles instead of the last paper you read.
- High autonomy and a bias to disagree;
Bonus: state-space model architecture, dynamic graphs, memory-augmented models, long-context, process mining, or graph neural networks. Experience designing benchmarks.
We believe someone with strong foundations can adapt to this work. If that’s you, and you want to work on the frontier of model-state interfaces, reach out.
