About the job
Join SuperDial as a Senior Staff Software Engineer, where you will lead the design and enhancement of backend systems that support large language model (LLM) applications in the healthcare sector. This position is perfect for an engineer who excels at the crossroads of backend architecture and applied artificial intelligence, focusing on creating reliable, secure, and cost-effective APIs and infrastructures for production-level LLMs. If you're eager to transform LLMs from mere demonstrations into essential components of critical healthcare workflows, we invite you to apply.
Key Responsibilities:
Backend Development for LLMs: Architect and develop scalable, low-latency APIs and services that wrap and optimize LLMs for healthcare applications.
Data & Retrieval Systems: Create ingestion, preprocessing, and retrieval-augmented generation (RAG) pipelines that integrate clinical and revenue-cycle data with LLMs.
LLMOps & System Monitoring: Design robust systems for model monitoring, evaluation, cost tracking, and operational guardrails to ensure reliability.
Performance Optimization: Engineer solutions for caching, batching, load balancing, and scaling LLM workloads across cloud environments.
Security & Compliance: Develop HIPAA-compliant infrastructures and data governance frameworks for LLM applications.
Collaborative Development: Work closely with product teams, ML engineers, and healthcare professionals to translate business needs into robust backend systems.
Technical Leadership: Oversee the complete delivery of LLM backend projects and mentor team members in best practices for LLM system design.
Your Profile:
5+ years of experience in backend or full-stack software engineering, including at least 3 years working with ML/LLM applications.
Proficient in Python and ideally one statically typed language such as Go, Java, or TypeScript.
Experience with LLM integration frameworks like Hugging Face, LangChain, or OpenAI APIs.
Solid understanding of distributed systems and service-oriented architecture, with experience in scalable API development.
Expertise in cloud-native technologies: AWS, GCP, Azure, Kubernetes, Docker, Terraform, etc.
Familiarity with MLOps practices, including CI/CD for models, evaluation harnesses, and monitoring.