Role:
LLM Scientist/Engineer

Position Type:
Full-Time Contract (40hrs/week)

Contract Duration:
Long Term

Work Schedule:
8 hours/day (Mon-Fri)

Location:
100% Remote

We are seeking an experienced LLM Engineer to design, develop, optimize, and deploy AI solutions using Large Language Models, with a strong focus on Retrieval Augmented Generation (RAG).

The idóneo candidate will have strong Python and AI/ML development experience, hands-on expertise with LLMs, RAG pipelines, vector databases, prompt engineering, and agent-based frameworks, along with experience building API-driven AI solutions on AWS.

Key Responsibilities
- Design and develop RAG-based LLM applications and information retrieval pipelines.
- Develop AI/ML solutions using Python and modern NLP/LLM technologies.
- Work with AWS Bedrock and LLM models to develop production-ready AI solutions.
- Build and optimize embeddings, vector search, and retrieval pipelines.
- Develop agent-based applications using frameworks such as LangChain.




- Perform prompt engineering and LLM fine-tuning for business-specific use cases.
- Build API-driven architectures for AI products and services.
- Collaborate with stakeholders to understand business requirements and translate them into AI solutions.
- Use ML frameworks such as PyTorch, TensorFlow, and Hugging Face.
- Apply Docker, Kubernetes, and CI/CD practices for AI application deployment.
- Communicate technical architectures and AI/data flows clearly to technical and business stakeholders.

Required
- 3+ years of Python experience.
- 3+ years of ML/AWS experience.
- 1+ year of hands-on NLP/LLM experience.
- Strong RAG experience.
- AWS Bedrock experience.
- LangChain or similar LLM/agent framework.
- Vector databases and embeddings.
- Prompt engineering and LLM fine-tuning.
- PyTorch, TensorFlow, or Hugging Face.
- Docker/Kubernetes and CI/CD exposure.
- Excellent communication skills.

📌 Generative AI Engineer (Argentina)
🏢 Sky Systems, Inc. (SkySys)
📍 Argentina