Remote Senior AI Engineer — LLM & RAG Architect

Proxify; Colombia; On-site; COP 357,487,577 - 500,482,607; Full time

Benefits offered by this job

On-time monthly payments

24 flex days off per year

Exclusive long-term positions at top companies

Job summary

Proxify is seeking a Senior AI Engineer to lead the development of LLM-powered solutions. Ideal candidates should have expert-level Python skills and experience with deploying production-level applications using Large Language Models. You will architect AI workflows, design optimization strategies for RAG pipelines, and develop high-performance backends to serve AI features to a global audience.

The position offers predictable project hours, flex days, and opportunities to work on exciting projects with leading companies while ensuring a harmonious work-life balance.

Qualifications

• Expert-level skills in Python programming and asynchronous programming.
• Experience building and deploying applications using LLMs in production.
• Strong familiarity with cloud AI model deployment.
• Ability to optimize vector databases for high-dimensional searches.

Responsibilities

• Architect and implement AI workflows using frameworks.
• Design optimization for RAG pipelines and vector database management.
• Evaluate model selection strategies based on performance criteria.
• Develop high-performance backends to serve AI features.
• Build frameworks to measure LLM accuracy and monitor performance.
• Collaborate with teams to implement AI solutions.

Skills

Expert-level Python skills

Experience with Large Language Models (LLMs)

Strong experience with SQL and NoSQL databases

Familiarity with cloud deployment (AWS, GCP, Azure)

Experience with fine-tuning open-source models

Knowledge of autonomous AI agents

Background in traditional NLP or Machine Learning

Tools

LangChain

LlamaIndex

Haystack

Pinecone

Weaviate

Milvus

FastAPI

Flask

LangSmith

Arize Phoenix

Job description

Proxify is seeking a Senior AI Engineer to lead the development of LLM-powered solutions. Ideal candidates should have expert-level Python skills and experience with deploying production-level applications using Large Language Models. You will architect AI workflows, design optimization strategies for RAG pipelines, and develop high-performance backends to serve AI features to a global audience.

The position offers predictable project hours, flex days, and opportunities to work on exciting projects with leading companies while ensuring a harmonious work-life balance.