Senior Software Engineer (Applied AI)

Pearl Health is dedicated to empowering primary care providers and health systems to succeed in value-based care. The Senior Software Engineer (Applied AI) will design and implement AI features, ensuring scalable and production-grade services that enhance healthcare outcomes.

Responsibilities:

• Design, build, and own production AI features powered by LLMs, including RAG architectures (chunking strategies, semantic search, vector databases) and Agentic workflows
• Develop high-performance data pipelines, APIs, and microservices that process healthcare data at scale and securely integrate LLM outputs into user-facing experiences
• Execute Proof-of-Concepts (POCs) and technical evaluations of new AI technologies to validate product viability and scalability
• Build responsive web applications using modern frontend frameworks to deliver intuitive, user-facing intelligence and analytic features
• Ensure observability, monitoring, and operational excellence for AI-powered services, championing security and regulatory compliance (HIPAA, SOC2)
• Drive architectural decisions and system optimizations for AI features in close collaboration with product and engineering leadership
• Own technical projects from discovery to delivery with autonomy, ensuring solutions align with business needs and long-term scalability
• Mentor and upskill fellow engineers on Applied AI best practices, fostering a strong culture of technical excellence and collaborative growth
• Contribute to the team's understanding of LLM capabilities, limitations, and best practices within the healthcare domain
• Participate in thorough design and code reviews, raising the bar for technical quality across the team
• Own and deliver complex technical projects with autonomy and accountability, ensuring successful delivery aligned with business timelines
• Identify and help resolve technical bottlenecks and cross-team dependencies that impact delivery velocity or system reliability
• Balance speed and quality, making pragmatic decisions that enable rapid iteration while maintaining engineering excellence

Requirements:

• 5-8+ years of professional experience in software engineering, with a strong foundation in service-oriented architectures and distributed systems
• Hands-on experience building and productionizing Applied AI/LLM features, including working with RAG architectures, vector databases, embedding models, and/or Agentic workflows
• Experience with observability and evaluation practices for production LLM systems (prompt tracking, quality metrics, cost monitoring)
• Strong proficiency in Python, relational databases, and a major cloud platform (AWS preferred)
• A deep understanding of modern service design principles, including RESTful and event-driven architectures
• Proven experience designing, building, and optimizing data-intensive applications
• A demonstrated history of mentoring engineers and driving technical best practices within a team
• A strong background in performance optimization, reliability engineering, and security best practices
• Experience building and deploying user-facing client applications using modern frameworks (e.g., React, Angular, Vue.js, TypeScript)
• A background working in healthcare technology, fintech, or another highly regulated industry
• Familiarity with compliance and security frameworks such as HIPAA or SOC2