The company is seeking a senior, product-minded engineer to join a small product squad consisting of 2 fullstack engineers and a PM.
The role involves owning features end-to-end, which includes designing, building, shipping, and iterating on backend services, web front-end, and internal tooling.
The engineer will be responsible for scaling the generative AI stack by productionizing retrieval-augmented generation pipelines, implementing evaluation harnesses, and hardening monitoring and alerting systems.
The position requires shaping the engineering culture by introducing best-in-class CI/CD, code quality standards, security practices, and mentoring.
Collaboration with product and sales teams is essential to translate real patient pain points into elegant solutions.
The engineer will influence the product roadmap by participating in product discovery, weighing technical trade-offs, and maintaining focus on impactful initiatives.
Requirements:
A minimum of 5 years of experience building and operating production software is required.
U.S. work authorization and residency are mandatory.
Proven experience in shipping large language model (LLM) or conversational AI products at scale, including LLM-APIs, vector stores, and agent frameworks.
Proficiency in Python and modern JavaScript is essential, along with familiarity with SQL and schema design.
Comfort with cloud infrastructure, preferably AWS, and infrastructure as code (IaC) is necessary.
A working knowledge of agents, vector search, embeddings, and retrieval-augmented generation performance tuning is required.
The candidate should have a good sense of product taste, particularly in user experience details.
Strong communication skills are needed to explain complex trade-offs to non-engineers.
Benefits:
The position offers a 401k match to support retirement savings.
The company promotes a remote-first culture, applicable to U.S. residents only.
There is an opportunity for the engineer to shape the technical and cultural foundation of the company.