GenAI Engineer (LLM) | Python | RAG | LangChain | AI Integration

KDK Software; Jaipur; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

KDK Software is seeking an AI Integration Engineer to build and scale LLM-powered SaaS applications from Jaipur. The role focuses on integrating LLMs, developing RAG pipelines, and ensuring secure, scalable AI-powered solutions.

You will work with teams to optimize performance, latency, and cost while implementing robust AI workflows and knowledge retrieval systems. This position emphasizes hands-on backend work and modern AI tooling.

Qualifications

• 3+ years backend development experience (Python/Go/Node.js).
• Experience with OpenAI, Claude, or Hugging Face.
• Hands-on with LangChain or LlamaIndex.
• Strong understanding of RAG and Vector Databases (Pinecone/Weaviate/pgvector).
• Experience with AWS, GCP, or Azure.
• Knowledge of APIs, Microservices, and Prompt Engineering.

Responsibilities

• Integrate LLM APIs for automation, parsing, and conversational AI.
• Design and optimize RAG pipelines and Prompt Engineering workflows.
• Build and manage Vector Databases for knowledge retrieval.
• Ensure AI application security, scalability, and performance.
• Monitor and optimize AI model quality, latency, and cost.
• Collaborate with Product and Engineering teams to deliver AI-powered features.

Skills

Vector databases

AI security

Performance monitoring

Education

Bachelor's or technical certs

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

OpenAI

Job description

We are looking for an AI Integration Engineer to build and scale LLM-powered SaaS applications. The role involves integrating LLMs, developing RAG pipelines, optimizing AI workflows, and building secure, scalable AI-powered solutions.

Key Responsibilities

• Integrate LLM APIs for automation, parsing, and conversational AI.
• Design and optimize RAG pipelines and Prompt Engineering workflows.
• Build and manage Vector Databases for efficient knowledge retrieval.
• Ensure AI application security, scalability, and performance.
• Monitor and optimize AI model quality, latency, and cost.
• Collaborate with Product and Engineering teams to deliver AI-powered features.

Experience Required

• 3+ years of backend development experience using Python, Go, or Node.js.
• Experience with OpenAI, Claude, or Hugging Face.
• Hands-on experience with LangChain or LlamaIndex.
• Strong understanding of RAG and Vector Databases such as Pinecone, Weaviate, or pgvector.
• Experience with AWS, GCP, or Azure.
• Knowledge of APIs, Microservices, and Prompt Engineering.

Preferred

• Experience in FinTech or SaaS.
• Exposure to LLMOps, Model Fine-tuning, CI/CD, and AI Observability.

Skills

• Vector Database Management
• AI Security & Compliance
• AI Performance Monitoring & Optimization

Education & Qualification

B.Tech / BCA / Technical Certification