Senior GenAI Engineer - Enterprise LLMs (Contract, NJ)

Intone Inc; New Jersey; Sur place; USD 120 000 - 180 000; Plein temps

Résumé du poste

Intone Inc is seeking a Senior GenAI Programmer for a 12-month contract in New Jersey to design, develop, and deploy generative AI and large language model solutions in enterprise production environments.

You will deliver end-to-end GenAI solutions, develop REST APIs with Python and FastAPI, and implement agentic AI workflows using LangGraph. The role emphasizes governance, risk controls, and scalable vector search/RAG architectures.

Qualifications

• 3+ years hands-on GenAI/LLM experience.
• Strong Python, REST APIs, FastAPI, and WebSocket skills.
• Experience with GPT/LLaMA and LangChain/LlamaIndex.
• Familiarity with embeddings, vector search, and RAG architectures.
• Knowledge of Model Governance and Model Risk Management practices.

Responsabilités

• Deliver end-to-end GenAI and LLM solutions in enterprise production environments.
• Develop and maintain REST APIs and WebSocket implementations using Python and FastAPI.
• Design and implement agentic AI systems and workflows using LangGraph and related frameworks.
• Build and optimize retrieval-augmented generation (RAG) systems, embeddings, and vector search solutions.
• Apply model governance and risk management practices, including documentation, compliance monitoring, and performance controls.

Connaissances

GenAI

LLM tech

Python

REST APIs

WebSockets

FastAPI

LangGraph

LlamaIndex

Embeddings

Vector search

RAG

Model governance

Model risk

Agentic AI

MCP

Outils

LangChain

LlamaIndex

Description du poste

Intone Inc is seeking a Senior GenAI Programmer for a 12-month contract in New Jersey to design, develop, and deploy generative AI and large language model solutions in enterprise production environments.

You will deliver end-to-end GenAI solutions, develop REST APIs with Python and FastAPI, and implement agentic AI workflows using LangGraph. The role emphasizes governance, risk controls, and scalable vector search/RAG architectures.