Gen AI Engineer - Boston, MA, Hartford, CT, Princeton, NJ, Newark, NJ, New York City, NY.
Job Title: GenAI Engineer Location: Boston, MA, Hartford, CT, Princeton, NJ, Newark, NJ, New York City, NY. Contact: 12+ Months Looking for W2 candidates. No C2C Job Summary We are looking for an experienced GenAI Engineer to design and build next-generation AI applications using Google Gemini, Vertex AI, and the Google Cloud Platform (Google Cloud Platform) ecosystem. The ideal candidate will have strong expertise in LangChain, LangGraph, Retrieval-Augmented Generation (RAG), agentic AI workflows, and scalable cloud-native architectures. This role involves building production-grade AI solutions, integrating LLMs into enterprise applications, and developing intelligent multi-agent systems. Key Responsibilities · Design, develop, and deploy Generative AI applications powered by Google Gemini (Pro, Flash, Ultra) and Vertex AI. · Build advanced prompt pipelines, RAG applications, and AI workflows using LangChain. · Design and implement stateful, multi-agent AI systems using LangGraph. · Develop scalable AI solutions utilizing Google Cloud services including Vertex AI Search, BigQuery, Cloud Run, Cloud Storage, and IAM. · Build robust data ingestion pipelines supporting multiple document formats. · Implement vector search architectures using Vertex AI Vector Search or vector databases such as Chroma, Milvus, Pinecone, Weaviate, or Qdrant. · Optimize LLM performance using prompt engineering, few-shot learning, and PEFT techniques. · Establish evaluation metrics for LLM accuracy, latency, hallucination detection, and model performance. · Implement LLMOps best practices including observability, scalability, monitoring, and security. · Develop REST APIs using FastAPI or Flask to expose AI services. · Collaborate with Product Managers, Data Engineers, and Front-End Developers to integrate AI capabilities into enterprise applications. Required Qualifications · Strong programming experience in Python. · Experience building REST APIs using FastAPI or Flask. · Hands-on experience with Google Gemini APIs, Vertex AI, and other enterprise LLM platforms. · Strong expertise with Langchain and LangGraph. · Experience implementing RAG architecture. · Strong knowledge of Google Cloud Platform (Google Cloud Platform). · Experience with Vertex AI, IAM, Cloud Run, BigQuery, and Google Cloud Storage. · Experience working with Vector Databases including Pinecone, Weaviate, Qdrant, Chroma, or Milvus. · Strong SQL and NoSQL database experience. · Experience debugging complex AI pipelines and distributed applications. · Strong problem-solving and communication skills. Preferred Qualifications · Google Cloud Professional Machine Learning Engineer Certification. · Google Cloud Professional Cloud Architect Certification. · Experience with Llama Index. · Experience with Hugging Face. · Experience with React and TypeScript. · Knowledge of Agentic AI architectures. · Experience with MLOps or LLMOps platforms. Required Skills · Python · Google Gemini · Vertex AI · Google Cloud Platform (Google Cloud Platform) · Langchain · LangGraph · FastAPI · Flask · RAG · Prompt Engineering · Vector Databases · Pinecone · Weaviate · Qdrant · Chroma · Milvus · BigQuery · Cloud Run · Google Cloud Storage · REST APIs Preferred Skills · Llama Index · Hugging Face · React · TypeScript · PEFT · LLMOps · Agentic AI · Vertex AI Vector Search · Few Shot Learning · Cloud Architecture Best Regards: Peerbhi SK Phone: Email: