Artificial Intelligence Engineer

• *Company Description**

CodeChavo is a global digital transformation and product engineering company delivering cutting-edge cloud, data, and AI solutions. We work with startups and enterprises to build scalable, secure, and production-ready digital products powered by modern technologies.

• *Role Description**

We are looking for an

• *AI Engineer**

with hands-on experience building production-grade LLM-based applications. The ideal candidate should have strong experience with OpenAI/Gemini APIs, Retrieval-Augmented Generation (RAG), agentic frameworks, and backend integration.

You will be responsible for delivering scalable, secure, and high-performance AI features in real-world production systems.

• *Key Responsibilities
• Design and develop
• *production-ready LLM-based applications
• Work extensively with
• *OpenAI / Gemini APIs**

for building AI features

• Implement
• *prompt engineering strategies**

for optimized LLM performance

• Build and optimize
• *RAG (Retrieval-Augmented Generation) pipelines
• Integrate AI capabilities into backend systems using
• *Node.js or Python
• Work with
• *vector databases**

(Pinecone, Weaviate, Milvus, etc.)

• Develop and integrate
• *MCP (Model Context Protocol) tools**
• Build AI agents using frameworks such as:

Pydantic-AI

LangGraph

• CrewAI
• Deploy AI services on cloud platforms (
• *AWS / GCP / Azure**

)

• Ensure scalability, security, monitoring, and performance optimization
• Collaborate with product and engineering teams for rapid feature delivery
• *Required Skills
• 2+ years of hands-on experience in AI/LLM-based development
• Strong experience with
• *OpenAI and/or Gemini APIs
• Practical implementation experience with
• *RAG architectures
• Experience with
• *vector databases
• Backend integration experience in
• *Node.js or Python
• Hands-on experience with
• *AI agentic frameworks (LangGraph, CrewAI, Pydantic-AI, etc.)
• Experience developing and integrating
• *MCP tools
• Strong understanding of API design and scalable architecture
• Ability to ship production-ready AI features quickly
• *Good to have

-

Experience fine-tuning or working with open-source LLMs

• Knowledge of embeddings, semantic search, and evaluation frameworks
• Exposure to AI observability and monitoring tools
• Experience in building enterprise AI solutions