Lead AI Engineer

Become a part of our caring community. You have shipped AI products before, understand the difference between a demo and a production system, and have strong opinions about evaluation frameworks from real‑world experience. You thrive when you own architecture decisions while continuing to build and deliver critical code yourself. We build the platform that transforms millions of clinical documents into trusted, actionable data using large language models (LLMs) to read medical records, extract structured facts, answer complex questions with citations, and route complex cases to human experts. The output supports healthcare decisions that impact real members.

Why Join Us

• Lead the architecture of production AI systems where LLMs are foundational.
• Make key technical decisions on model selection, system boundaries, platform architecture, and build‑versus‑buy strategies.
• Own the highest‑risk and highest‑impact challenges involving reliability, explainability, and correctness.
• Influence engineering culture and establish standards for building and shipping AI products.
• Work on systems operating at meaningful scale, processing millions of documents and supporting healthcare decisions across a large member population.
• Partner with highly skilled engineers while remaining deeply hands‑on in coding, design, and production operations.
• Simplify complex solutions and drive pragmatic engineering decisions that maximize business value.

Key Responsibilities

• Own the architecture, design, and evolution of full‑stack AI applications, including LLM pipelines, retrieval systems, agentic workflows, human‑in‑the‑loop processes, and supporting platform services.
• Design and implement scalable AI solutions that prioritize reliability, accuracy, auditability, performance, and cost efficiency.
• Build and maintain the most complex and high‑risk system components where architecture and implementation decisions have significant business impact.
• Define and enforce engineering standards for AI systems, covering evaluation methodologies, structured outputs, observability, testing, fallback strategies, latency optimization, and cost controls.
• Lead technical design reviews and guide architecture decisions related to platform capabilities, AI systems, integrations, infrastructure, and software patterns.
• Evaluate and recommend technologies, frameworks, AI models, and third‑party solutions based on technical and business requirements.
• Translate ambiguous business goals into clear technical strategies, roadmaps, and executable workstreams.
• Provide technical leadership across multiple projects, ensuring alignment with architectural standards and long‑term platform objectives.
• Mentor and coach engineers through design reviews, code reviews, pair programming, and technical guidance.
• Partner with product, engineering, clinical, and operational stakeholders to deliver solutions that meet business and regulatory requirements.
• Own operational excellence, including deployment strategies, monitoring, incident management, and production reliability.
• Ensure all solutions comply with privacy, security, governance, and audit requirements within a regulated healthcare environment.

Required Qualifications

• Bachelor’s degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.
• 8+ years of software engineering experience, including designing and operating production systems at scale.
• Proven track record of delivering AI‑enabled products or platforms into production environments.
• Deep hands‑on experience integrating and operating LLMs within business‑critical workflows.
• Experience designing systems that leverage structured outputs, tool calling, retrieval‑augmented generation (RAG), agentic workflows, orchestration frameworks, and evaluation pipelines.
• Experience making architectural decisions for systems where AI is a core component of the product experience.
• Demonstrated success leading technical initiatives across engineering teams, including architecture reviews, technical planning, mentoring, and delivery execution.
• Strong programming skills in Python and/or TypeScript/JavaScript.
• Experience designing and operating distributed systems, APIs, data platforms, and cloud‑native applications.
• Strong understanding of reliability engineering, system performance, scalability, and operational excellence.
• Ability to balance technical trade‑offs involving quality, latency, cost, security, and maintainability.

Preferred Qualifications

• Experience taking AI products from concept through production deployment and long‑term operational ownership.
• Experience developing AI systems where LLMs are part of critical decision‑support or operational workflows.
• Expertise in evaluation frameworks, benchmark datasets, regression testing, model quality measurement, and human review processes.
• Experience with agentic systems, Model Context Protocol (MCP), workflow orchestration, multi‑step reasoning frameworks, and AI observability platforms.
• Experience with React, Next.js, modern frontend technologies, and full‑stack application development.
• Experience deploying and managing workloads using Kubernetes, Docker, modern CI/CD platforms, and cloud‑native technologies.
• Experience with Google Cloud Platform, Azure, AWS, Vertex AI, or comparable AI and cloud infrastructure platforms.
• Experience working in highly regulated industries such as healthcare, financial services, or government.
• Knowledge of privacy, compliance, security, and governance frameworks impacting AI and data‑driven applications.
• Experience implementing AI‑assisted development practices that improve engineering productivity and delivery speed.
• Excellent communication, collaboration, problem‑solving, and leadership skills.

Leadership Expectations

• Lead through technical excellence, sound engineering judgment, and hands‑on execution.
• Establish standards that drive consistency, reliability, and quality across the engineering organization.
• Influence architectural direction while balancing innovation with operational stability.
• Foster a culture of ownership, continuous learning, mentorship, and accountability.
• Drive alignment across teams and stakeholders to ensure successful delivery of strategic initiatives.

Success in This Role

Successful candidates are passionate about building production‑grade AI systems where correctness, transparency, and reliability matter. They enjoy solving difficult engineering problems, making thoughtful architectural decisions, and helping teams deliver high‑impact solutions. They are equally comfortable defining system architecture, mentoring engineers, reviewing designs, responding to production incidents, and writing code for the most critical parts of the platform.

Technology Stack

• TypeScript
• React / Next.js
• Python
• PostgreSQL
• Gemini on Vertex AI
• OCR and Document AI technologies
• Docker
• Kubernetes
• Modern CI/CD platforms and tooling

Work Style & Schedule

This position follows a hybrid work schedule, requiring employees to work three days per week in the office and the remaining days remotely. Candidates must reside within, or be willing to relocate to, a commutable distance from one of the talent markets.

Pay

Base salary range: $170,800 – $234,800 per year. This range reflects a good‑faith estimate for full‑time (40 hours per week) employment and may vary based on geographic location, experience, education, certifications, and other factors. The role is also eligible for a performance‑based bonus incentive plan.

Benefits

• Medical, dental, and vision coverage
• 401(k) retirement savings plan
• Paid time off, company and personal holidays, paid parental and caregiver leave
• Short‑term and long‑term disability
• Life insurance
• Additional whole‑person well‑being programs and resources