Pasito is the AI workspace for employee benefits.
We’re rethinking how group insurance and benefits are underwritten, delivered, used and measured - by the people who design them and the people who depend on them. Instead of static PDFs, disconnected systems, and manual workflows, Pasito brings plan design, payroll and benefits data, claims, and financial context into a single, AI‑native workspace that helps benefits actually work for the 178 million Americans who depend on this system.
We don’t build for brokers, carriers and employers - we build with them. That collaboration shows up in everything we ship: AI agents that extract and structure plan data, tools that turn complexity into clarity for employees, and workflows that save carriers and consultants hundreds of hours per case.
Today, Pasito supports many of the largest insurance carriers and brokers in the U.S. We’re backed by Y Combinator and Core Innovation Capital, and we’re growing quickly. We ship fast, iterate relentlessly, and care deeply about building systems that are accurate, scalable, and human.
If you’re excited to work alongside exceptional operators and engineers, and apply AI in a legacy industry where precision and trust matter, Pasito is the place for you.
About the roleAs an AI/ML Engineer, you’ll work across backend systems, data pipelines, and AI/ML systems. You’ll help architect and build multi-agent systems, work across LLM development, agent orchestration, evaluation and deployment, owning the full development from prototype to production.
As an early member of the engineering team, you’ll have real ownership and influence: shaping architecture, defining standards, and building systems that carriers, brokers, and employers rely on every day.
What You’ll DoDevelop AI-native workflows
Architect and build scalable multi-agent systems with clear evaluation metrics, monitoring, fallback strategies, and cost controls for extracting and reasoning over complex benefits data.Own backend and data-heavy systems
Design and own backend services, APIs, and data pipelines that power AI workflows, with a focus on correctness, scalability, observability, and long-term maintainability.Collaborate cross-functionally
Work closely with Product, Design, Sales, and Client teams to understand customer workflows and translate them into durable technical solutions.Continuously improve systems
Refine existing architecture, reduce operational complexity, and help define what “great” looks like as the platform scales.
A full stack engineer with 3+ years of experience building complex web applications
Comfortable owning backend systems and APIs, while collaborating closely on frontend experiences
Experienced integrating AI / LLM-powered systems into real products
Curious, adaptable, and energized by working in fast-moving, ambiguous environments
A collaborative partner to product managers, designers, and other engineers
3+ years of experience in software engineering
Strong backend engineering experience with Node.js and Python. Hands-on experience integrating and operating AI systems using frameworks such as LangGraph, LangChain, LlamaIndex, and model SDKs (OpenAI, Anthropic, Google AI Studio), including prompt/version management and tool calling. Bonus: AWS, MySQL at scale, and JavaScript frameworks.
Experienced building, deploying, and operating multi-step or multi-agent AI systems in production, with ownership of correctness, latency, cost, and failure handling
Experienced designing and operating RAG or persistent memory systems using vector databases (e.g., Pinecone, Turbopuffer), including indexing strategies, retrieval evaluation, and performance/cost tradeoffs
Experienced building production-grade evaluation and monitoring pipelines for AI systems (e.g., LangSmith, Langfuse, MLflow), including offline evals, live metrics, and regression detection
Experience building document ingestion pipelines, structured extraction, chunking strategies, and handling noisy or inconsistent source documents
Curious, adaptable, and energized by working in fast-moving, ambiguous environments
A collaborative partner to product managers, designers, and other engineers
Experience in insurance, healthcare, or financial services is a plus, but not required.
What’s In It For YouMeaningful ownership: Build foundational systems used by carriers, brokers, employers, and employees at scale
Real impact: Your work directly improves how people understand and use their benefits
Growth: Join early and grow with the company as we scale our product, team, and distribution
Silver screening Interview
Silver Technical Interview
Client Screening Interview
Client Technical interview
Client Behavioral Interview
Skills Required
- 3+ years of experience in software engineering
- 3+ years building complex web applications as a full stack engineer
- Strong backend engineering experience owning services and APIs
- Proficiency with Node.js
- Proficiency with Python
- Hands-on experience integrating and operating AI/LLM systems using LangGraph, LangChain, LlamaIndex and model SDKs (OpenAI, Anthropic, Google AI Studio)
- Experience building, deploying, and operating multi-step or multi-agent AI systems in production, with attention to correctness, latency, cost, and failure handling
- Experience designing and operating RAG or persistent memory systems using vector databases (e.g., Pinecone, Turbopuffer)
- Experience building production-grade evaluation and monitoring pipelines for AI systems (e.g., LangSmith, Langfuse, MLflow)
- Experience building document ingestion pipelines, structured extraction, chunking strategies, and handling noisy source documents
- Experience with AWS, MySQL at scale, and JavaScript frameworks
- Experience in insurance, healthcare, or financial services
What We Do
Silver.dev is a technology company focused on developing, maintaining, and distributing mobile applications as its core product, tackling deep tech challenges.
