AI Engineer – Google AI & Generative Intelligence
Role summary
Seeking a Senior AI Engineer with 10-15 years of software engineering experience and 3+ years in Generative AI to design, build, and deploy production-grade AI systems using Google AI technologies. The role requires expertise in the Google ecosystem (Workspace, Vertex AI, ADK), LLM/SLM frameworks (LangChain, Semantic Kernel), MLOps, and cloud-native development on GCP. Responsibilities include developing AI agents, integrating with Google Workspace, building APIs, implementing RAG pipelines, and ensuring code quality and testing. Experience with multi-agent architectures and vector databases is crucial. The position is a hybrid contract/full-time role in Paramus, NJ.
Job Title: AI Engineer – Google AI & Generative Intelligence
Location: Paramus, NJ – Hybrid (local/nearby preferred)
Type: Contract/Full-time Any
Experience Level: 10–15 years in software engineering, 3+ years in Generative AI
Job Description
Role Overview:
We are seeking a Senior AI Engineer with deep expertise in Google AI technologies and Generative AI to design, build, deploy, and monitor production‑grade AI systems. The ideal candidate will have mastery of the Google ecosystem (Workspace, ADK, Vertex AI), strong command of LLM/SLM frameworks, and hands‑on experience with cloud‑native infrastructure and MLOps practices.
Key Responsibilities
• AI Engineering: Design, develop, and deploy agents leveraging Gemini, GPT, Claude Sonnet for multimodal tasks.
• Google AI & Workspace Integration: Architect AI solutions integrated with Google Workspace (Docs, Sheets, Drive, Gmail, Meet), BigQuery, Lakehouse. Build intelligent agents using Google ADK.
• Design & Planning: Lead requirements gathering (Confluence), create architecture diagrams (Lucidchart), manage delivery/sprints (Jira).
• Development Frameworks & Tools: Orchestrate LLM/SLM apps with LangChain, LlamaIndex, LangGraph. Build multi‑agent systems with Semantic Kernel. Manage prompts with LangSmith/PromptLayer.
• Vector Databases & Semantic Search: Implement RAG pipelines using Vertex AI Vector DBs, ChromaDB. Optimize enterprise knowledge retrieval.
• Backend Development: Build RESTful APIs with FastAPI (Python) or Express.js (Node.js). Manage APIs with MuleSoft/Apigee.
• Frontend Development: Drupal CMS (PHP + JS), React/Angular, Material‑UI, OAuth2 authentication.
• Development Tools & Code Quality: Use VS Code with Copilot, GitHub/GitLab for versioning, enforce standards with SonarQube, ESLint, Pylint.
• Testing & QA: Conduct LLM testing with RAGAS, DeepEval, LangSmith Evaluators. Write unit tests with pytest. Ensure reliability with hallucination detection and custom metrics.
• Deployment & Infrastructure: Support deployments across GCP (Vertex AI), hybrid, on‑prem, and edge AI environments.
Required Qualifications
•
10–15 years of software engineering experience
• 3+ years in Generative AI (LLMs, SLMs, RAG, multi‑agent systems)
• Deep expertise in Google AI ecosystem (Gemini, Vertex AI, ADK, AI Studio, Workspace)
• Proficiency in Python, familiarity with Node.js
• Strong background in cloud‑native development on GCP
• Experience with multi‑agent architectures (Semantic Kernel, LangGraph)
Preferred Qualifications
• Google Cloud Certifications (Professional ML Engineer / Cloud Architect)
• Contributions to open‑source AI/ML projects
• Experience with edge AI and hybrid deployments
• Experience building enterprise AI platforms or Centers of Excellence
• Strong leadership and mentoring experience
Key-Required Skills Summary:
• Generative AI (LLMs, SLMs, RAG, Agents)
• Google Cloud AI Stack (Vertex AI, Gemini, ADK, AI Studio)
• AI Frameworks (LangChain, LangGraph, LlamaIndex, Semantic Kernel)
• MLOps & Observability (LangSmith, MLflow, W&B)
• Cloud & Infrastructure (GCP, Kubernetes, Serverless)
• Backend & APIs (FastAPI, Node.js, Apigee, MuleSoft)
• Frontend (React, Angular, Drupal, Material‑UI)
• Vector DBs (BigQuery, ChromaDB, Vertex AI Vector Search)