Generative AI (Gen AI) Architect || Raritan, NJ (Onsite)

Position: Generative AI (GenAI) Architect

Location: Raritan, NJ (Onsite)

Live Python Coding test during the Interview

Job Description :

Key Responsibilities

• GenAI Architecture: Design end-to-end architectures for Generative AI applications, including LLMs, RAG pipelines, AI agents, and multi-agent systems.
• LLM Integration: Work with models such as GPT, Claude, Gemini, and open-source models like Llama.
• RAG Implementation: Build document ingestion, chunking, embedding, vector search, retrieval, reranking, and response-generation pipelines.
• AI Agent Development: Design intelligent agents using frameworks such as LangChain, LangGraph, and Semantic Kernel.
• Cloud AI Solutions: Architect and deploy solutions using Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Vector Databases: Integrate vector stores such as Pinecone, Azure AI Search, Weaviate, or FAISS.
• Enterprise Integration: Connect GenAI applications with APIs, databases, enterprise systems, and knowledge repositories.
• Security and Governance: Implement data privacy, access controls, responsible AI practices, guardrails, and protection against prompt injection.
• Performance Optimization: Optimize model latency, token consumption, inference costs, scalability, and response quality.
• MLOps and LLMOps: Establish CI/CD pipelines, model evaluation, monitoring, observability, and production deployment practices.
• Technical Leadership: Define architecture standards, conduct design reviews, mentor developers, and collaborate with business and engineering teams.