Experience Level: Lead (8-10+ Years)
Core Stack: GCP (Vertex AI, Cloud Run, GKE), Python, Agentic Frameworks (LangChain/LangGraph, LlamaIndex, AutoGen), Vector DBs, Payer Systems (EDI/FHIR, Claims, Prior Auth)
Required Qualifications & ExperienceCore AI/ML & Agentic Engineering (Must-Have)- 8+ Years in software/AI engineering, with 3+ years directly building, deploying, and maintaining production-grade LLM applications, RAG pipelines, or autonomous agent frameworks.
- Agentic Frameworks: Hands-on mastery of multi-agent orchestration patterns, tool calling, stateful graphs, and memory management (e.g., LangGraph, AutoGen, LlamaIndex, Semantic Kernel).
- GCP AI Ecosystem: Deep experience with Vertex AI (Model Garden, Endpoint Deployment, Vector Search, Workbench) and cloud-native services (Cloud Run, Pub/Sub, Cloud Functions).
- Production Python Engineering: Advanced Python expertise (AsyncIO, FastAPI, Pydantic, gRPC) writing clean, tested, and containerized microservices.
Domain & Architecture Focus- Healthcare / Payer Domain: Proven familiarity with Payer workflows (Prior Authorization, Claims Processing, Appeals, Member Engagement) and health data standards (FHIR, EDI X12, ICD-10/CPT).
- Data & Retrieval: Experience with vector indexing, hybrid search, reranking strategies, and chunking optimization for massive unstructured document stores.
- Security & HIPAA: Deep understanding of HIPAA compliance, PHI handling, and data privacy in AI pipelines.
Nice-to-Have / Force Multipliers- GCP Cloud Architecture: Experience with Terraform, GCP VPCs, and IAM fundamentals.
- Fine-Tuning & Small Language Models (SLMs): Experience fine-tuning domain-specific models (PEFT, LoRA) for structured extraction or classification.
- Evaluation & Evals Frameworks: Deep experience with automated LLM benching and continuous integration testing for probabilistic software.
- Certifications: GCP Professional Machine Learning Engineer or GCP Professional Cloud Architect credential.
