Principal Real-Time AI Platform Engineer

9025 CVS Shared Services Resources LLC; Massachusetts; On-site; USD 144,200 - 288,400; Full time

Job summary

CVS Health is seeking a Principal Software Engineer to drive hands-on technical leadership for real-time, multi-service clinical platforms deployed on Google Cloud. You will design, code, ship production features, and mentor engineers across UI, backend, and ML to improve reliability and clinical impact.

The role emphasizes performance, scalability, and governance, with responsibilities spanning architecture, LLM pipelines, event-driven services, and CI/CD processes, while collaborating with

Qualifications

• 10+ years of software engineering experience delivering production systems at scale.
• 5+ years as a hands‑on Staff or Principal‑level engineer (actively coding, not removed from implementation).
• Expert proficiency in Python including performance tuning, concurrency, and system optimization.
• 5+ years building real‑time distributed systems (event‑driven, streaming, Pub/Sub) with clear latency and reliability requirements.
• 5+ years working in a major public cloud (GCP preferred: Vertex AI, GKE, Cloud Run, Pub/Sub, BigQuery, IAM).
• Deep experience with microservices architecture, API design (REST), and resilient systems (retries, backpressure, tracing).
• 3+ years building and operating production ML systems (MLOps, monitoring, retraining, deployment pipelines).
• 3+ years developing LLM-powered applications in production, including prompt design, RAG/vector search, evaluation frameworks, and performance optimization
• Experience building modern UI components with React or Angular
• Strong computer science fundamentals, including distributed systems, algorithms, and concurrency

Responsibilities

• Own architecture and execution of a real-time, multi-service clinical platform on GCP, building the most critical components.
• Build production-grade LLM pipelines, including prompt engineering, evaluation, retrieval, OCR-based understanding, grounding, guardrails, and mitigating hallucinations.
• Deliver real-time, high-performance services with sub-second clinician experiences under heavy load, with strict SLOs and fault tolerance.
• Operationalize models on Vertex AI, including feature pipelines, drift detection, A/B/shadow testing, and CI/CD quality controls.
• Design for scalable APIs, microservices, and data contracts with strong testing, observability, and progressive delivery.
• Raise the engineering bar through code reviews, standards across testing/CI/CD/security/observability, and mentoring across full-stack and ML.
• Own outcomes end-to-end by translating clinical needs into delivered solutions and iterating based on data.
• Collaborate with Data Science, Product, Clinical SMEs, AI Governance, and Security to meet enterprise standards for compliance and safety.

Skills

Python

Distributed systems

LLM systems

GCP

API design

Microservices

UI with React/Angular

CI/CD

Mentoring

Algorithms & CS fundamentals

Education

Bachelor's degree in Computer Science or related field

Master’s or PhD in CS/ML (a plus)

Job description

CVS Health is seeking a Principal Software Engineer to drive hands-on technical leadership for real-time, multi-service clinical platforms deployed on Google Cloud. You will design, code, ship production features, and mentor engineers across UI, backend, and ML to improve reliability and clinical impact.

The role emphasizes performance, scalability, and governance, with responsibilities spanning architecture, LLM pipelines, event-driven services, and CI/CD processes, while collaborating with