Senior Research Scientist
Contact us at
About Us
Syntracts is an AI-powered legal-tech startup on a mission to deliver on the unfulfilled promise of legal AI, reshaping how top firms turn their most valuable asset, their contracts, into structured, actionable intelligence.
We don’t just wrap third-party APIs. We’re building a foundational stack for legal data question answering. With backing from top VCs in NYC, SF, and Boston, our proprietary platform uses stacked of custom trained specialized RAG systems hundreds and fine-tuned language models to structure complex legal knowledge from documents with unparalleled accuracy. It’s built for the enterprise: secure, scalable, and deployable entirely on-premises.
This is a unique opportunity to join as one of our early team members and help shape not just our operations, but also our culture, processes, and trajectory.
The Role
As a Research Scientist at Syntracts, you’ll work at the core of our mission: building and training our proprietary platform to extract precise, verifiable answers from complex legal contracts. You’ll help build and refine the full machine learning stack that powers this capability, from identifying and linking relevant sections of contracts to generating structured, machine-readable answers that can be trusted by top law firms.
Your work will span multiple layers of our data and model pipeline. You’ll develop and experiment with models that locate and connect the clauses containing answers, even when information is scattered across a document, and design systems that transform those insights into structured data.
You’ll create and leverage synthetic datasets, evaluate different LLMs and retrieval-augmented generation architectures, and build post-processing models that score, rank, and validate answer accuracy.
This is a hands-on research role where you’ll explore everything from custom LLM training to new approaches like our proprietary “reverse RAG” models and graph-based reasoning systems. If you’re excited by open-ended technical challenges and the opportunity to turn raw legal text into structured intelligence at scale, this is the place to do it.
This role reports directly to the VP of AI and is fully remote, with occasional travel for team events.
Responsibilities
Design, build, and refine the systems that extract structured, verifiable answers from complex legal contracts.
Work across the full ML stack, from data preparation tomodel development to evaluation and post-processing — to develop scalable research prototypes and translate them into production-ready systems.
Evaluate, fine-tune, and experiment with large language models (LLMs) to determine the best architectures and training strategies for extracting accurate answers.
Conduct data engineering and experimentation to determine optimal data sources and configurations.
Develop and maintain automated post-processing and scoring systems that rank model performance before results reach downstream validation.
Collaborate with engineers and researchers to design ranking systems, RAG models, and graph-based reasoning frameworks that improve precision and reliability.
Prototype and test novel architectures that support the company’s long-term research roadmap, balancing rigor with practical application.
Document findings, share insights, and contribute to the continual improvement of Syntracts’ research infrastructure and methodologies.
Experience & Skills
Strong engineering background with the ability to design, implement, and iterate on complex ML systems.
Deep understanding of the distinction between building a research product and a software engineering product — able to prioritize experimentation, flexibility, and rapid iteration over rigid scalability.
Demonstrated ability to write reusable, modular, and adaptable code that supports ongoing research and future development.
Proven experience working across the machine learning lifecycle — from data wrangling and labeling to model training, validation, and deployment.
Hands-on experience with LLM-centric development, including tools and frameworks such as Hugging Face, Transformers, and the Python ML ecosystem.
Strong understanding of data engineering fundamentals, including creating datasets, managing labeled data, and structuring inputs for model training.
Comfortable operating in cloud environments and working with virtual machines and clustered compute systems; experience with Kubernetes is a plus.
Ability to collaborate with domain experts such as lawyers to translate conceptual needs into data specifications and model requirements.
Familiarity with training, validation, and evaluation loops in applied ML workflows.
Excellent problem-solving skills, intellectual curiosity, and a research-oriented mindset focused on innovation and technical rigor.
Why Join Us
Be a true partner in shaping a company from day one
Competitive salary + meaningful equity
Direct collaboration with experienced founders and mission-driven team
Salary Range: Competitive salary plus a performance bonus and equity, commensurate with experience
Benefits:
Health, dental, and vision insurance
Flexible PTO and remote work options
We aim to offer a total compensation package that is competitive to companies at our same stage and reflects the value you bring to the team.
How to Apply
Excited about this opportunity? We’d love to hear from you! Please email your resume to careers@syntracts.com.
Equal Employment Opportunity
Syntracts is proud to be an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, gender identity or expression, age, marital status, veteran status, disability status, or any other characteristic protected by law. We believe diverse teams build stronger companies and strongly encourage candidates from all backgrounds to apply.