AI Engineer

Blue Cross Blue Shield of Massachusetts•Boston, MA

7d•$140,310 - $171,490

About The Position

Blue Cross Blue Shield of Massachusetts is seeking an AI Engineer to join its AI Engineering team. The role focuses on designing, building, and deploying intelligent AI assistants using Google Cloud Platform (GCP) and Vertex AI, combining large language models, cloud infrastructure, and product engineering to deliver conversational AI experiences that provide business value. The engineer will develop assistants and multi-step agents using Vertex AI and the Google Agent Development Kit (ADK), integrate Google Cloud AI/ML SDKs, and build agentic architectures with tool use, sub-agents, and session management. The role also includes connecting agents to enterprise APIs, databases, and external services; applying responsible AI practices; designing scalable production solutions on GCP; and developing evaluation and monitoring approaches for quality, latency, cost, and user satisfaction. The engineer will collaborate with product managers, data engineers, and business stakeholders and assess emerging AI models, tools, and techniques.

Requirements

Bachelor's or master's degree in Computer Science, Machine Learning, Data Science, or a related field, or equivalent practical experience.
At least 5 years of software engineering experience, including at least 2 years focused on AI/ML or LLM-based agentic development.
Hands-on experience with GCP services, particularly BigQuery, Cloud Storage, Cloud Run, or Cloud Functions.
Hands-on experience with Vertex AI Agent Builder, Vertex AI Search, or Dialogflow CX.
Experience with Google Cloud SDKs, including Vertex AI SDK and Google Gen AI SDK, for model invocation, tuning, and deployment workflows.
Strong proficiency in Python and familiarity with ML/AI frameworks and libraries such as LangChain, LlamaIndex, TensorFlow, or PyTorch.
Experience building LLM-based agentic applications, including prompt engineering, function calling, embeddings, and retrieval-augmented generation.
Solid understanding of API design, microservices architecture, and cloud-native development patterns.
Familiarity with Git, CI/CD pipelines, and Infrastructure as Code such as Terraform or Cloud Build.
High school degree or equivalent is required unless otherwise noted above.

Nice To Haves

Google Cloud certifications, such as Professional Machine Learning Engineer or Professional Cloud Architect.
Exposure to multi-agent architectures, tool-use patterns, and agentic AI frameworks.
Experience with vector databases such as Vertex AI Vector Search, AlloyDB, Pinecone, or Weaviate, and embedding-based retrieval.
Knowledge of MLOps practices, including experiment tracking, model versioning, A/B testing, and production monitoring.
Experience in regulated industries such as healthcare, finance, or insurance, with understanding of data privacy and compliance requirements.

Responsibilities

Design and develop AI assistants using Vertex AI, including model selection, prompt engineering, grounding, retrieval-augmented generation (RAG), and agent orchestration.
Build multi-step AI agents with the Google Agent Development Kit (ADK), including agent architectures with tool use, sub-agents, callbacks, and session management.
Develop and integrate applications using the Vertex AI SDK for Python and Google Gen AI SDK to access foundation models, embeddings, tuning, and prediction endpoints.
Design agentic architectures using sequential agents, loop agents, parallel agents, and custom agent hierarchies for multi-turn, multi-domain use cases.
Implement tool and function calling patterns that connect agents to enterprise APIs, databases, and external services.
Implement responsible AI practices, including safety filters, bias detection, guardrails, hallucination mitigation, and content moderation.
Architect scalable, production-grade solutions using Vertex AI Agent Builder, Vertex AI Search, Cloud Run, Cloud Functions, Pub/Sub, BigQuery, and other GCP services.
Develop production evaluation and monitoring frameworks to measure assistant quality, latency, cost, and user satisfaction, including use of ADK evaluation and tracing capabilities.
Collaborate with product managers, data engineers, and business stakeholders to translate requirements into AI-powered solutions.
Stay current with the AI landscape, evaluate emerging models, tools, and techniques, and recommend adoption where appropriate.