Job Description & Details
Artificial intelligence is reshaping every industry, and expertise in building agentic systems with large language models is in high demand. Companies are racing to integrate retrieval‑augmented generation (RAG) pipelines and graph‑based knowledge stores to unlock smarter applications. This Agentic AI Developer role offers a chance to lead cutting‑edge projects on Google Vertex AI while working onsite in New Jersey.
Job Summary
We are seeking a senior‑level Agentic AI Developer with deep Python expertise to design, implement, and optimize Retrieval‑Augmented Generation (RAG) solutions on Google Vertex AI. The role focuses on integrating graph and vector datastores, building scalable pipelines, and delivering production‑grade AI agents for enterprise clients.
Top 3 Critical Skills Table
| Skill | Why it's critical | Mastery Level |
|---|---|---|
| Python | Core language for AI model development & orchestration | Senior |
| Vertex AI (RAG) | Platform for building scalable retrieval‑augmented generation pipelines | Senior |
| Graph/Vector Datastores | Enables semantic search & knowledge‑graph integration for intelligent agents | Senior |
Interview Preparation
- Explain how you would design a RAG pipeline on Vertex AI. What the interviewer is looking for: Understanding of data ingestion, embedding generation, vector store indexing, and prompt engineering.
- What are the trade‑offs between using a graph database vs. a vector store for knowledge retrieval? What the interviewer is looking for: Knowledge of graph traversal, semantic similarity, latency, and scalability considerations.
- Walk me through a Python code snippet that streams embeddings into a vector datastore in real time. What the interviewer is looking for: Ability to write production‑ready, asynchronous Python and handle API rate limits.
- How do you monitor and troubleshoot model drift in a live RAG system? What the interviewer is looking for: Experience with logging, evaluation metrics, and automated retraining pipelines.
- Describe a situation where you had to optimize inference latency for an AI agent. What techniques did you use? What the interviewer is looking for: Practical performance tuning (batching, quantization, caching, hardware selection).
Resume Optimization
- Agentic AI
- Python
- Vertex AI
- Retrieval‑Augmented Generation (RAG)
- Graph Datastore
- Vector Store
- Machine Learning
- AI Engineer
- Large Language Models
- H1B Visa
Application Strategy
When emailing the recruiter, start with a brief greeting, attach your updated resume, and clearly highlight how your background aligns with the role. Make sure to mention related skills you possess, such as Python development, Vertex AI RAG experience, and graph/vector datastore integration. Reference any relevant projects where you built end‑to‑end AI pipelines and emphasize your 10+ years of industry experience.
Career Roadmap
| Current Role | Typical Experience | Core Focus | Next Position |
|---|---|---|---|
| Agentic AI Developer (Python) | 10+ years AI/ML, Python, Vertex AI | Build RAG pipelines, graph/vector integration | Senior AI Engineer |
| Senior AI Engineer | 5‑7 years leading projects | Architecture, mentorship, scaling solutions | AI Lead / Manager |
| AI Lead / Manager | 3‑5 years managing teams | Strategy, product vision, cross‑functional delivery | Director of AI |
| Director of AI | 5+ years leadership | Organization‑wide AI roadmap, budget, innovation | VP of AI / CTO |