2-5 years of professional software development experience, primarily in Python.
Proficient with LLM APIs, agent frameworks, and modern retrieval patterns.
Proven ability to deliver impactful work in ambiguous situations.
Experience with user-facing products, either backend or full-stack.
Strong interest in building rigorous evaluation infrastructure.
Curiosity-driven; no prior insurance experience required, but a willingness to learn is essential.
Excellent written and spoken English skills.
Responsibilities
Diagnose product shortcomings and analyze root causes for improvements.
Design and refine tool-calling patterns for multi-step research tasks.
Build ingestion and normalization systems for complex structured documents at scale.
Develop reinforcement fine-tuning harnesses and train graders for research tasks.
Measure, profile, and optimize agent pipeline performance across millions of calls.
Run end-to-end experiments and translate findings into product recommendations.
Engage directly with customers to gain insights into their needs.
Benefits
Health insurance, including dental and vision coverage for family.
401K company match.
Life insurance coverage.
Cell phone and internet reimbursement.
25 days of paid time off per year.
Commuter benefits.
Gym membership via ClassPass.
IT equipment allowance.
Opportunities for professional development and training.
Regular team gatherings and events.
Full Job Description
Insurance pricing depends heavily on unstructured regulatory and market data - filings, forms, exhibits, bulletins, and countless other documents that are hard to search, interpret, and operationalize.
We're building the OS for pricing: systems that reliably transform tens of millions of messy documents into queryable, trustworthy intelligence embedded directly in pricing workflows.
Our AI team is small, talent-dense, and operates with real ownership. We maintain open-source projects with thousands of stars and publish work recognized across the AI ecosystem. The problems we work on are active research areas where no one has great answers yet.
You'll own the full feedback loop: diagnose where the product falls short, rigorously analyze root causes, build evaluations, and ship improvements that customers feel.
The work spans agent systems, evaluation and data quality, and production engineering in roughly equal measure.
You'll work directly with customers when it helps you understand the problem deeply - we believe engineers should have a clear line of sight to the people using what they build.
The type of projects that you can expect to work on:
Design and refine tool-calling patterns and agent orchestration to handle multi-step research tasks that requires reasoning across thousands of related documents.
Build ingestion and normalization systems for complex structured documents at scale - millions of filings where formats vary and each version builds on the last.
Build and iterate on reinforcement fine-tuning harnesses, including training graders for research tasks with non-verifiable reward.
Develop tooling to measure, profile, and optimize agent pipeline performance - latency, cost, and quality across millions of calls.
Run experiments end-to-end: design, analyze, and translate into clear product recommendations.
Why this role ?
You'll work on genuinely hard, unsolved problems at the intersection of AI systems and a massive real-world data domain.
You'll ship to production regularly, talk to customers, and see your work change how people make consequential decisions.
The team is small enough that your judgment directly shapes the product - and we're building it to be best in class.
*This role is a hybrid position to be based in New York City, with a necessity for 3 days a week of office presence.
Candidates must be team players with strong interpersonal skills,as well as:
2 - 5 years of experience building software professionally, with strong programming fundamentals (we work mostly in Python).
Proficiency with LLM APIs, agent frameworks, and modern retrieval patterns. You stay current as the field moves. We don't need classical ML expertise - we need someone on the frontier of applied AI.
Strong track record of shipping high-impact work in ambiguity. You take a vague problem, define what "good" looks like, ship a v0, and iterate.
Experience shipping user-facing products, either backend or full-stack.
Drawn to the question "how do we know this is actually better?" - excited to build the evaluation infrastructure that answers it rigorously.
Curiosity over domain experience. No insurance background needed - you learn fast and care about understanding the problem space deeply.
Strong written and spoken English
As a newcomer, you'll be joining a diverse, highly skilled and motivated team, with a strong Tech DNA, colleagues that are eager to share their knowledge and passion.
We care about strong teamwork and a positive day-to-day environment. The team regularly connects through optional activities such as team lunches, sports, karaoke, or occasional after-work gatherings.
In addition to this, we will provide you with:
Competitive salary + annual bonus
Health insurance , Dental and Vision coverage (including spouse and family coverage)
401K Company match
Life insurance
Cell Phone & Internet reimbursement
25 days of PTO/year
Commuter benefit
Gym membership via ClassPass
IT equipment allowance
Professional development & trainings
Team fun: regular company gatherings and team events
