Staff Software Engineer, Applied AI

SuperDial

2d•$200,000 - $275,000

About The Position

SuperDial is seeking a Staff Software Engineer, Applied AI to build and scale backend systems that power LLM applications in healthcare. The role focuses on backend architecture and applied AI, including the APIs, pipelines, and infrastructure needed to make LLMs reliable, secure, and cost-efficient in production. The engineer will help move LLMs beyond demonstrations and into mission-critical healthcare workflows. The position includes architecting scalable, low-latency services for healthcare LLM applications; building ingestion, preprocessing, and retrieval-augmented generation pipelines grounded in clinical and revenue-cycle data; and developing monitoring, evaluation, cost-tracking, and guardrail systems. It also involves optimizing LLM workloads through caching, batching, load balancing, and scaling across cloud and containerized environments, and implementing HIPAA-ready infrastructure, data governance, and auditability. The Staff Software Engineer will collaborate with product teams, ML engineers, and healthcare experts to translate business workflows into robust backend systems. The role also leads end-to-end delivery of LLM backend projects, establishes engineering best practices, and mentors peers in LLM system design. SuperDial is transforming healthcare AI with scalable solutions to optimize revenue cycle management.

Requirements

At least 5 years of backend or full-stack software engineering experience, including at least 3 years working on ML/LLM-enabled applications.
Strong coding skills in Python.
Deep knowledge of distributed systems, service-oriented architecture, and building APIs at scale.
Cloud-native expertise with technologies such as AWS, GCP, or Azure; Kubernetes; Docker; and Terraform.
Familiarity with MLOps/LLMOps practices, including model CI/CD, evaluation harnesses, monitoring, and reproducibility.
Excellent system design skills and ability to align technical architecture with product goals.

Nice To Haves

Experience with a statically typed language such as Go, Java, or TypeScript.
Experience with LLM integration frameworks and services such as Hugging Face, LangChain, LlamaIndex, OpenAI APIs, or Anthropic.
Experience applying LLMs in healthcare or other regulated industries, including FHIR, HL7, or HIPAA.
Hands-on experience with RAG pipelines, vector databases, and structured-output orchestration.
Background in enterprise SaaS or mission-critical platforms where uptime, latency, and scale matter.
Knowledge of responsible AI, safety, and privacy-preserving ML techniques.

Responsibilities

Architect and implement scalable, low-latency APIs and services that wrap, orchestrate, and optimize LLMs for healthcare use cases.
Build ingestion, preprocessing, and retrieval-augmented generation (RAG) pipelines that ground LLMs in clinical and revenue-cycle data.
Design model monitoring, evaluation, cost-tracking, and guardrail systems to support reliability and responsible use.
Optimize LLM workloads through caching, batching, load balancing, and scaling across cloud and containerized environments.
Implement HIPAA-ready infrastructure, data governance, and auditability for LLM-powered applications.
Partner with product, ML engineering, and healthcare teams to translate business workflows into robust backend systems.
Drive end-to-end delivery of LLM backend projects, establish engineering best practices, and mentor peers in LLM system design.