Senior GenAI Engineer - Remote Production-grade LLM

Look4IT; United States; A distancia; USD 160.000 - 210.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

100% remote

B2B contract

Long-term engagement

Live LLM product

Modern AI/LLM stack

Flexible working environment

Descripción de la vacante

Look4IT is seeking a Senior AI Engineer for a fully remote role building and operating a production-grade LLM system used by real users. You will drive end-to-end features from concept to deployment, focusing on answer quality, performance, observability and cost efficiency.

You will work with LangGraph, RAG, tool calling, Azure OpenAI, Gemini and Claude, shaping how AI-powered products are built and operated in production.

Formación

• Experience building and operating backend services and APIs.
• Hands-on production experience taking LLM features to live production.
• Experience with cloud platforms, ideally Azure, and cost-aware optimization.
• Familiarity with LangGraph, RAG, tool calling and streaming services.
• Strong problem-solving, analytics and decision-making in production systems.

Responsabilidades

• Build end-to-end LLM-powered features and deploy as services with testing.
• Own answer quality by evaluating prompts, models and retrieval pipelines.
• Turn user questions into effective queries against search platforms and orchestrate loops.
• Debug production, monitor latency, token use and cost budgets across model variants.

Conocimientos

Backend development

APIs

Async programming

Testing

LLM production

LangGraph

RAG

Azure

English communication

Herramientas

LangGraph

Azure OpenAI

FAISS

PostgreSQL

Langfuse

Azure App Insights

Bicep

Docker/Podman

FastAPI

Python

Descripción del empleo

Look4IT is seeking a Senior AI Engineer for a fully remote role building and operating a production-grade LLM system used by real users. You will drive end-to-end features from concept to deployment, focusing on answer quality, performance, observability and cost efficiency.

You will work with LangGraph, RAG, tool calling, Azure OpenAI, Gemini and Claude, shaping how AI-powered products are built and operated in production.