13 days ago
Base Salary
$101k - $194k/yr
Responsibilities
- Architect and deploy scalable multi-agent AI systems with agent workflows, A2A communication protocols, and task delegation hierarchies.
- Integrate LLMs with enterprise systems using APIs, function calling, and the Model Context Protocol.
- Build and operate enterprise Agent Factory pipelines for continuously executing intelligent workflows.
- Design and implement RAG systems using ONNX-based embeddings and vector databases.
- Manage short-term, medium-term, and long-term agent memory and state using tools such as LangGraph.
- Own feature engineering, model training, production deployment, and continuous monitoring across the agent and model lifecycle.
- Establish security guardrails, permission boundaries, short-lived agent identity tokens, and safety constraints.
- Develop propensity models, classification systems, and forecasting solutions for agent decision-making.
- Translate AI outputs into operational strategies and present findings to senior leadership and business partners.
- Perform AI-augmented analytics and generative AI model validation for accuracy, reliability, and business performance.
Requirements
- Bachelor's degree or four or more years of work experience.
- At least four years of relevant experience, including two or more years focused on generative AI, LLMs, and autonomous agent systems.
- At least four years developing and implementing analytical or AI solutions for complex business problems.
- Hands-on proficiency with LangChain, LangGraph, Google Agent Development Kit, LlamaIndex, or AutoGen.
- Experience with A2A communication protocols, task delegation hierarchies, MCP, agent memory, state management, context-window optimization, and stateful workflows.
- Knowledge of RAG, ONNX-based embeddings, Pinecone, Weaviate, pgvector, and semantic search.
- Knowledge of BigQuery pipelines and GCP, including Cloud Run and Vertex AI, or Amazon Bedrock or an Azure equivalent.
- Experience with Python and SQL for statistical modeling, prompt engineering, token management, and large-scale data extraction.
- Preferred qualifications include a quantitative Master's degree, ML/LLM monitoring and observability experience, AI testing and model validation, LLMOps, AI governance and security, ROI modeling, commercial analytics, and executive communication skills.
Benefits
- Hybrid work arrangement with work from home and a minimum of three days per week in the office.
- Medical, dental, vision, disability, life insurance, AD&D, identity theft protection, pet insurance, and group home and auto insurance options.
- Matched 401(k), up to eight company-paid holidays, up to six personal days, paid parental leave, adoption assistance, tuition assistance, and other incentives.
- Newly hired employees receive up to 15 vacation days per year, increasing with additional service.
- Full-time schedule is 40 hours per week.
Tech Stack
Categories
About Verizon
Verizon builds and operates wireless networks, broadband (Fios), and enterprise connectivity, security, and IoT solutions for consumers, businesses, and public-sector customers. Its revenue comes from subscription mobile services, internet and TV access, and managed network and cloud security offerings. Founded in 2000 via the Bell Atlantic–GTE merger, the public company (NYSE: VZ) is headquartered in Basking Ridge, New Jersey, and is one of the largest mobile carriers in the United States.