Software Engineer Generative AI

CORUS Consulting; Colombia; Remote; COP 244,021,473 - 406,702,456; Full time

Job summary

An innovative consulting firm is on the lookout for a talented Software Engineer specializing in Generative AI. This exciting role involves developing cloud-native platforms tailored for cutting-edge AI technologies. You will work with advanced LLMs and contribute to creating scalable, efficient systems that drive impactful solutions. If you have a strong background in software engineering and a passion for AI, this position offers a unique opportunity to shape the future of technology in a fully remote environment across Latin America. Join a dynamic team and make your mark in the world of AI!

Qualifications

• 5+ years of experience in Generative AI and LLM development.
• Strong background in cloud-native platforms and microservices.
• Expertise in building secure data ingestion pipelines for unstructured data.

Responsibilities

• Develop and maintain cloud-native platforms for Generative AI.
• Build scalable and reliable systems for LLM development.
• Create enterprise-grade data ingestion pipelines and knowledge graphs.

Skills

Generative AI

Large Language Models (LLMs)

Python

TypeScript

Node.js

React.js

APIs

Cloud Infrastructure

DevOps/MLOps/LLMOps

Advanced English Proficiency

Tools

AWS Bedrock

Azure OpenAI

OpenAI

LangChain

LlamaIndex

Kubernetes

Docker

Job description

Corus Consulting is a consulting firm with more than 15 years of experience working with clients worldwide; we have a presence in Europe, the United States, Asia, and Mexico.

We are seeking talented individuals to join us as:

Software Engineer Generative AI

Description:

We are looking for a highly skilled and experienced full-stack Software Engineer with expertise in Generative AI and Large Language Models (LLMs) to join our Gen AI platform team. This role involves building and maintaining cloud-native platforms specifically designed for Generative AI and LLM development. The ideal candidate will have a strong background in reusable software components, frameworks, microservices, APIs, cloud infrastructure, and DevOps/MLOps/LLMOps, with a passion for creating scalable, reliable, and efficient systems.

Location:

Fully Remote in Mexico, Colombia, or Brazil

Must-Have Requirements:

• Advanced English proficiency
• Proven experience in Generative AI and LLM-based development
• Strong knowledge in building conversational agent-based UX
• Experience working with key LLM model APIs (e.g., AWS Bedrock, Azure OpenAI, OpenAI) and frameworks (e.g., LangChain, LlamaIndex)
• Experience with multi-agent frameworks and understanding of multi-agent systems for complex problem-solving
• Expertise in building enterprise-grade, secure data ingestion pipelines for unstructured data, including indexing, search, and advanced retrieval patterns
• Proficiency in working with text embeddings, understanding embedding spaces, and their applications in semantic search and information retrieval
• Experience in building production knowledge graphs
• Knowledge of RAG concepts and fundamentals (VectorDBs, AWS OpenSearch, semantic search) and implementing RAG systems combining knowledge bases with Generative AI
• Proficiency in Python, TypeScript, Node.js, React.js (and similar frameworks), and relevant GenAI libraries
• Experience with containerization and orchestration technologies such as Kubernetes and Docker

Seniority level:

• Mid-Senior level

Employment type:

• Full-time

Job function:

• Information Technology

Industries:

• IT Services and IT Consulting