Applied Research Engineer, Agents

The Team

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.

What We’ve Built

• A custom multi-agent framework powering everything from deep research capabilities to copiloting interfaces paired with distributed systems infrastructure for long running agentic tasks.
• 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.
• Elastically scaling data representation and metadata generation > powering the most effective private data retrieval systems.
• Industry leading agents problems from buy side company diligence to multi billion dollar M&A.

The Role

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.

Responsibilities

• Focused on LLMs, you will play a crucial role in analyzing and interpreting complex data types to derive and implement cutting edge insight generation systems.
• Iterate and explore new LLM and NLP techniques maintaining our foothold as an industry leader
• You will utilize your expertise in statistics, programming, and machine learning to develop and deploy data-driven models and algorithms
• Your work will contribute to solving business problems, improving processes, and enhancing the overall performance of the company
• Collaborate with cross-functional teams to improve NLP/LLM capabilities in app
• Stay up-to-date with the latest advancements and research in the space
• Collaborate with software engineers to integrate agentic capabilities into existing systems or develop new applications
• Ensure that systems are efficient, maintainable and well monitored.
• Iterate on validation and testing frameworks.

Who You Are

• Bachelor's degree in Computer Science, Engineering, or related field
• Master’s degree in Computer Science, Mathematics, Machine Learning or a related field is a plus.
• 7+ years software development experience at a venture-backed startup or top technology firm, with a focus on applied machine learning systems
• Strong programming skills in Python
• Experience with NLP and text processing libraries such as NLTK, SpaCy, or Apache Tika
• Experience with Search and Indexing technologies
• Proficient in machine learning techniques and algorithms
• Experience working with foundational models and corresponding APIs
• Knowledge of statistical analysis and data scraping techniques
• Prior experience in developing NLP models and systems
• Experience with prompting and building LLM applications and agents is a plus.
• Excellent problem-solving and analytical skills
• Strong communication and teamwork abilities
• Strong capability to translate research into production software systems
• Bonuses:
• Experience building agentic systems or LLM enabled products.
• Frequent user of AI products, especially during the development lifecycle (i.e. Cursor, Claude Code, etc).

Compensation

The salary range for this role is $160,000 to $300,000. This range may be inclusive of several career levels at Hebbia and will be narrowed during the interview process based on the candidate’s experience and qualifications. Adjustments outside of this range may be considered for candidates whose qualifications significantly differ from those outlined in the job description.

• LIFE @ HEBBIA
• PTO: Unlimited
• Insurance: Medical + Dental + Vision + 401K

Eats: Catered lunch daily + doordash dinner credit if you ever need to stay late

Parental leave policy: 3 months non-birthing parent, 4 months for birthing parent

Fertility benefits

• $15k lifetime benefit
• New hire equity grant: competitive equity package with unmatched upside potential
• #LI-Onsite