Hebbia enables leading finance and legal firms with advanced reasoning, copiloting and retrieval capabilities - unlocking meaningful insights for meaningful use cases. The Agents team builds everything from core document understanding capabilities to co-piloting experiences for matrix and deep, multi-source research. We’ve built our own agentic frameworks powered by distributed systems built for scale.
We don’t build for one-off success. We build steerable, reliable and explainable agentic systems. And we build these systems for the scale of data our customers bring to the table. Our goal is to unlock the unknowable unknown for customers all over the world.
We want to build a product that becomes indisposable to our customers and as delightful as your favorite consumer product. We move fast and build first of their kind systems.
1.
A custom multi-agent framework powering everything from deep research capabilities to copiloting interfaces paired with distributed systems infrastructure for long running agentic tasks.
2.
The world’s most powerful and scalable LLM inference engine - a distributed, asynchronous DAG orchestrator capable of incorporating live graph mutations, cooperating in tandem with our LLM throughput management capabilities.
3.
Elastically scaling data representation and metadata generation → powering the most effective private data retrieval systems.
4.
Industry leading agents solving problems from buy side company diligence to multi billion dollar M&A.
As an Applied Research Engineer, you will be the bridge between research, industry, and application shaping the future of our core natural language processing systems. You will be responsible for enabling agentic capabilities across the Hebbia product suite. You will own experiments and POCs focused on combining the latest research findings with specific high value problems that our customers encounter each and every day. You will leverage our deep relationships with foundation model providers - partnering to beta test models, experiment with new features, and develop guidance on relative model strengths
This role requires prior expertise in NLP, machine learning systems, and LLM evaluation; experience building with foundation models and experience working with Attention based NLP models is a plus. This role is best suited for an individual who can excel at both running experiments with novel LLM techniques as well as building production grade, LLM-enabled software systems - embedding directly in the software development lifecycle.