Lead Software Engineer, Agentic AI Systems

Lead Software Engineer, Claims AI Automation

Collective Health is revolutionizing healthcare benefits through integrated technology, compassionate service, and exceptional user experience. We are advancing our Claims AI Automation team from traditional rule-based adjudication to an intelligence-driven platform and seeking a Lead Software Engineer to drive this transformation.

What You Will Do:

• Execute Agentic Workflows: Build and deploy sophisticated AI agents using Google Vertex AI and the Google Agent SDK (ADK) based on architectural specifications.
• Develop AI Agent Behaviors: Optimize agent behaviors using Gemini (Pro/Flash) with a focus on reliable tool-calling and multi-step reasoning. Implement RAG and grounding strategies for factual, data-driven responses from internal claims databases and policy documents.
• Enhance Agent Precision: Design and implement complex system instructions, few-shot prompting, and Chain-of-Thought reasoning for high-precision claims logic. Perform Supervised Fine-Tuning on Gemini models for improved domain-specific performance in adjudication and medical coding.
• Data & Messaging: Utilize SQL/PostgreSQL/AlloyDB/BigQuery. Understand architectural decisions and drive reusable patterns for cloud-native, AI-enabled backend systems.
• Stateful Orchestration: Design and implement stateful orchestration patterns with human review breakpoints, enabling agents to pause, persist state, and resume workflows after auditor approval.
• Input/Output Guardrails: Implement guardrails and 'Circuit Breaker' logic to detect and intercept non-compliant agent behavior or toxic/hallucinated outputs in real-time.
• PHI Protection: Implement Google Cloud DLP or similar tools within AI pipelines to ensure Patient Health Information (PHI) is never exposed to the model’s training or logs.

To Be Successful, You’ll Need:

• Expert Python Developer: Exceptional skills in building production-grade applications using frameworks like LangChain, LangGraph, or PydanticAI.
• Gemini & Vertex AI Experience: Hands-on experience building with the Gemini model family and the Google Agent SDK (ADK).
• Vertex AI Mastery: Deep experience with the Vertex AI Python SDK, specifically Reasoning Engine (Runtime), Extensions, and Function Calling.
• Prompt Engineering Skills: Proven ability to engineer high-performance prompts that mitigate hallucinations and ensure deterministic outputs in regulated environments.
• Full-Stack Experience: 8+ years of full-stack experience with a heavy focus on backend systems.
• AI-First SDLC: Mastery of AI-enhanced development tools (e.g., Cursor, WindSurf, GitHub Copilot).

Preferred Qualifications:

• Familiarity with healthcare interoperability standards and claims-related data structures.
• Practical experience in fine-tuning LLMs for specific industry nomenclature or structured output formats.
• Working knowledge of Java and Spring Cloud for supporting existing microservice architectures.

Our Tech Stack:

• AI & LLMs: Gemini, Vertex AI, Google ADK, Python, LangChain.
• Existing Backend: Java, Spring Cloud, Spring Boot.
• Data & Messaging: PostgreSQL, Spark, AlloyDB, BigQuery.
• Infrastructure: GCP (Vertex AI, GKE, Cloud Run), Docker.

Location & Compensation:

• This is a hybrid position based out of our Lehi or Plano offices, requiring at least two weekdays per week in the office.
• Pay Range (Lehi, UT): $138,000—$172,500 USD
• Pay Range (Plano, TX): $151,800—$189,750 USD
• Additional Compensation: Eligible for 205,000 stock options.

Why Join Us?

• Mission-driven culture fostering innovation, collaboration, and excellence in healthcare.
• Impactful projects shaping the future of our organization.
• Opportunities for professional development, internal mobility, mentorship, and tailored courses.
• Flexible work arrangements and supportive work-life balance.

Collective Health is an equal opportunity employer. Please visit https://jobs.collectivehealth.com/benefits/ to learn more about our benefits.