Senior Generative AI Engineer Remote — LLM & RAG Architect

Hire Feed; Argentina; Presencial; ARS 211.388.000 - 317.082.000; Jornada completa

Descripción de la vacante

Hire Feed is seeking a Senior LLM Engineer to design, build, and deploy generative AI solutions in a fully remote, full-time role. Work on LangChain, RAG pipelines, and modern LLM frameworks while shaping the technical roadmap with cross-functional teams.

The ideal candidate has deep Python/SQL expertise, strong understanding of LLM internals, and experience deploying AI systems on cloud platforms like AWS, Azure, or GCP.

Formación

• Proficient in Python and SQL for AI system development.
• Experience with LangChain and modern LLM frameworks.
• Deep understanding of LLM internals, including prompt tuning, embeddings, vector databases, and agent workflows.
• Background in machine learning or software engineering with system-level thinking.
• Experience working with cloud platforms such as AWS, Azure, or GCP.

Responsabilidades

• Design and develop generative AI and LLM-based systems using tools such as LangChain and retrieval-augmented generation (RAG) pipelines
• Implement prompt engineering techniques and agent-based frameworks to deliver intelligent, context-aware solutions
• Collaborate with the engineering team to shape and drive the technical roadmap for LLM initiatives
• Translate business needs into scalable, production-ready AI solutions
• Contribute to architecture discussions, code reviews, and performance optimization

Conocimientos

Python

SQL

Cloud platforms

Herramientas

LangChain

LLM frameworks

Vector databases

Embeddings

Descripción del empleo

Hire Feed is seeking a Senior LLM Engineer to design, build, and deploy generative AI solutions in a fully remote, full-time role. Work on LangChain, RAG pipelines, and modern LLM frameworks while shaping the technical roadmap with cross-functional teams.

The ideal candidate has deep Python/SQL expertise, strong understanding of LLM internals, and experience deploying AI systems on cloud platforms like AWS, Azure, or GCP.