Generative AI Architect

Hi,

This is Praveen from Pronix Inc !!

Position: Generative AI Architect/ Data Scientist - W2 only

Location: Plano TX, Charlotte NC, Pennington NJ (Hybrid 3 days in office and 2 days remote)

Employment Type: Long term Contract

Job Description

We are looking for a Generative AI Architect to design and scale a next-generation Document AI platform for the financial industry. You will lead the architecture of solutions for document classification, data extraction, and retrieval-augmented generation (RAG), ensuring performance, compliance, and auditability in a highly regulated environment.

Responsibilities:

• Architect enterprise GenAI solutions for classification, extraction, and Q&A over large document sets
• Build and optimize RAG pipelines with embeddings, vector DBs, and rerankers
• Partner with infrastructure teams to deploy on GPU clusters (vLLM, Triton)
• Drive model risk management: explainability, audit trails, and evaluation pipelines
• Create architecture diagrams, technical documents, and executive presentations
• Collaborate with engineering, product, and compliance teams to deliver safe, scalable AI

Requirements:

• 8+ years in software/solution architecture, with 3+ in AI/ML or GenAI
• Hands-on experience with LLMs, embeddings, and vector search (OpenAI, Hugging Face, Llama, Elastic Search)
• Strong proficiency in Python (FastAPI, LangChain)
• Experience with GPU optimization, cloud-native deployment, and MLOps
• Strong communication skills with the ability to present to executives

Ph : 609-378-1142 (Six Zero Nine Three Seven Eight One One Four Two)