Staff Software Engineer – Backend Systems (Applied AI / Healthcare)

Location: San Francisco, CA (4 days in office)
Client: Ashton North’s client

About the Opportunity

Ashton North’s client is seeking a Staff Software Engineer to design, build, and scale backend systems that power Large Language Model (LLM) applications in the healthcare sector. This is a high-impact role for an engineer who thrives at the intersection of backend architecture and applied AI—developing APIs, pipelines, and infrastructure that make LLMs reliable, secure, and cost-efficient in production.

If you’re passionate about taking LLMs beyond demos and embedding them into mission-critical healthcare workflows, this role offers the chance to shape the future of AI-driven innovation in a regulated, high-stakes environment.

Key Responsibilities

• Backend Architecture for LLMs: Design and implement scalable, low-latency APIs and services that orchestrate, optimize, and secure LLMs for healthcare applications.

• Data & Retrieval Pipelines: Build data ingestion, preprocessing, and retrieval-augmented generation (RAG) pipelines to ground LLMs in clinical and revenue-cycle datasets.

• Systems Reliability: Drive high availability, observability, and fault tolerance across distributed systems handling sensitive healthcare data.

• Operational Excellence: Apply best practices in MLOps and LLMOps—ensuring continuous integration, evaluation, and monitoring of models in production.

• Cross-Functional Collaboration: Partner closely with AI researchers, product teams, and healthcare domain experts to translate requirements into robust technical solutions.

Qualifications

Experience:

• 5+ years of backend or full-stack software engineering experience.

• 3+ years of hands-on experience developing ML or LLM-enabled applications.

• Proven experience applying LLMs in healthcare or other regulated industries (FHIR, HL7, HIPAA familiarity preferred).

Technical Skills:

• Strong coding proficiency in Python.

• Experience with LLM integration frameworks and RAG pipelines.

• Deep understanding of distributed systems, API design, and microservices architecture.

• Expertise with cloud-native technologies (AWS, GCP, or Azure) and container orchestration (Kubernetes, Docker, Terraform).

• Familiarity with MLOps/LLMOps concepts including CI/CD for models, evaluation harnesses, and reproducibility.

• Additional coding proficiency in a statically typed language (Go, Java, or TypeScript) is a plus.

Education:

• Bachelor’s degree in Computer Science or a related technical field from a leading institution.

Soft Skills & Attributes

• Strong communication and collaboration skills—comfortable interfacing directly with customers and internal stakeholders.

• Highly analytical with the ability to balance speed and precision in complex, data-driven environments.

• Entrepreneurial mindset with a drive to build systems that push AI into real-world production.

Work Environment

• This is an on-site role requiring 4 days per week in the San Francisco office.