GenAI / AI Platform Architect

Boston Scientific is at the forefront of innovation, leveraging AI to revolutionize healthcare and deliver cutting-edge solutions. We are seeking an experienced GenAI / AI Platform Architect to establish, build, and continuously refine a secure, governable, and enterprise-grade Generative-AI platform. This platform will support critical use cases including copilots, Retrieval-Augmented Generation (RAG) search, intelligent document processing, and agentic workflows.

Key responsibilities include:

• Defining the reference architecture for GenAI, encompassing LLM hosting, vector databases, orchestration layers, real-time inference, and evaluation pipelines.
• Designing and governing RAG pipelines, including embedding generation, indexing, hybrid retrieval, and prompt assembly, to ensure authoritative and auditable responses.
• Selecting and integrating toolchains such as LangChain, LangGraph, LlamaIndex, MLflow, Kubeflow, and Airflow, ensuring compatibility with cloud GenAI services like Azure OpenAI, Amazon Bedrock, and Vertex AI.
• Implementing MLOps/LLMOps practices for automated CI/CD of model fine-tuning, evaluation, rollback, and blue-green deployments, integrating model performance monitoring and drift detection.
• Embedding security and responsible AI guardrails early in the development lifecycle, including PII redaction, model output moderation, lineage logging, bias checks, and policy-based access controls, in collaboration with CISO and compliance teams.
• Optimizing cost-efficiency through dynamic model routing, context window compression, and GPU/Inferentia auto-scaling, and publishing charge-back dashboards for business units.
• Mentoring solution teams on prompt engineering, agentic patterns (e.g., ReAct, CrewAI), and multi-modal model integration (vision, structured data).
• Establishing evaluation frameworks (e.g., LangSmith, custom pipelines, human-in-the-loop) to track relevance, hallucination, toxicity, latency, and carbon footprint.
• Reporting key performance indicators (KPIs) such as MTTR for model incidents, adoption growth, and cost per token, and iterating on the roadmap in partnership with product, data, and infrastructure leads.

Required Qualifications:

• Over 10 years of experience designing cloud-native platforms or AI/ML systems, with at least 3 years leading large-scale GenAI, LLM, or RAG initiatives.
• In-depth knowledge of LLM internals, fine-tuning, Reinforcement Learning from Human Feedback (RLHF), and agentic orchestration patterns (e.g., ReAct, Chain-of-Thought, LangGraph).
• Proven experience with vector database architectures (e.g., Pinecone, Weaviate, FAISS, pgvector, Milvus) and semantic search optimization.
• Proficiency in Python and API engineering, with hands-on experience with LangChain, LlamaIndex, FastAPI, GraphQL, and gRPC.
• Solid background in security, governance, and observability across distributed AI services, including IAM, KMS, audit trails, and OpenTelemetry.

Preferred Qualifications:

• Relevant certifications such as AWS Certified GenAI Engineer – Bedrock or Microsoft Azure AI Engineer Associate.
• Experience orchestrating multi-modal models (images, video, audio) and streaming inference on edge devices or medical sensors.
• Contributions to open-source GenAI frameworks or published white papers on responsible AI design.
• Familiarity with FDA or HIPAA compliance for AI solutions in the healthcare industry.
• Demonstrated ability to influence executive stakeholders and lead cross-functional teams in a rapidly evolving AI market.