Position summary

RxSense is becoming an AI native company, and AI is the primary lever behind our next phase of growth.

This is a deeply technical, architect level role. You will sit on the AI Engineering team and set the technical standard the broader engineering organization looks to, leading through example and craft rather than mandate. You will architect and build systems across our stack (C#/.NET, Python, and the occasional TypeScript front end), and you will lead development of our AI evaluation infrastructure, both offline (test suites, golden datasets, and regression harnesses wired into CI/CD) and online (continuous monitoring of live model and system behavior).

Working in this domain is compelling because two things must hold true at once. Our systems need to be correct, since we operate in a regulated, high stakes domain where evaluation and trustworthy behavior matter as much as the features themselves. Our systems also need to be fast, since they run at high volume and low latency, where performance compounds at scale. Much of this role is about helping projects move quickly while staying confident in the products we ship.

You will do this work in an AI forward environment. Our engineers build with modern agentic tooling standardized on Anthropic's Claude, so you will have first class tools for the work ahead.

Responsibilities

• Architect and build production systems across a multi language stack: C#/.NET services, Python AI and data pipelines, and occasional TypeScript
• Set the example for an AI forward, high technical standard across the broader engineering organization, leading through craft rather than organization wide authority
• Design and drive adoption of offline evaluation frameworks (test suites, golden datasets, regression harnesses wired into CI/CD) for LLM based and other non deterministic components
• Build online evaluation and monitoring that continuously assesses live model and system behavior in production, including drift and regression detection
• Partner with engineering leadership to surface systemic risks in AI features, such as reliability, correctness, and drift, and drive the fixes
• Lead architecture reviews for major initiatives and mentor senior and staff engineers on system design, evaluation methodology, and AI forward practices
• Prototype and ship new AI capabilities

What success looks like

Day to day, you move between writing production code, shaping architecture across teams, and building the evaluation tooling that gives RxSense confidence in its AI systems before and after they ship. 

Qualifications

• 8+ years of professional software engineering experience, with demonstrated Staff, Principal, or Architect-level scope — e.g., owning system architecture end-to-end, driving technical strategy across multiple teams, or being accountable for critical production systems. We evaluate candidates on the scope and impact of their work rather than years of experience alone; strong candidates with less tenure but clear evidence of this level of ownership are encouraged to apply. 
• Depth across backend and AI/ML systems, working in some combination of C#/.NET, Python, and TypeScript.
• Experience with LLM observability, prompt and response evaluation, or agentic system testing
• A track record of setting technical standards that other engineers and teams adopt.
• Strong communication skills, with the ability to align engineers and leadership around a shared technical direction.
• Comfort working in an AI forward engineering environment, for example with agentic coding tools such as Claude Code.
• Bachelor's degree in Computer Science, Engineering, or a related field preferred. Equivalent practical experience will be considered in lieu of a formal degree. 

Preferred

• Experience in pharmacy benefits, healthcare, fintech, or another regulated, high stakes domain.
• Familiarity with distributed systems tooling such as Kafka, gRPC, Grafana, and Dragonfly / Redis.
• A good eye for clean, usable interfaces for the occasional front end work.

Salary Range- $210,000- $275,000