AI Engineer-(Fullstack-Python, Node, React/Angular)-Immediate

Kezan Consulting; Dadri, Gurugram District; On-site; INR 3,000,000 - 5,000,000; Full time

Job summary

Kezan Consulting is seeking an AI Engineer with 5+ years of software development experience for a Gurgaon-based hybrid role. You will design AI-powered apps using LLMs and RAG, build robust backends in Python and Node.js, and integrate AI with enterprise systems.

The candidate will implement end-to-end AI pipelines, optimize performance and latency, and collaborate with frontend teams to deliver scalable solutions.

Qualifications

• 5+ years of software development experience.
• Strong proficiency in Python and Node.js.
• Hands-on experience with LLMs (OpenAI, Claude, Gemini, Llama, etc.).
• Experience building RAG-based applications using vector databases such as Pinecone, Qdrant, Chroma, or FAISS.
• Good understanding of APIs, microservices, and cloud-native application development.
• Familiarity with prompt engineering, embeddings, and AI application evaluation.

Responsibilities

• Design and develop AI-powered applications using LLM, RAG, and vector databases.
• Build backend services and APIs using Python and Node.js.
• Implement document ingestion, chunking, embeddings, retrieval, and prompt orchestration pipelines.
• Integrate AI solutions with web applications and enterprise systems.
• Optimize model performance, response quality, latency, and scalability.
• Collaborate with frontend developers (React/Angular) and cross-functional teams for end-to-end delivery.
• Follow best practices for testing, deployment, monitoring, and security of AI applications.

Skills

Python

Node.js

Large Language Models

Retrieval-Augmented Generation

Job description

AI Engineer 5+ Years

Location: Gurgaon / Hybrid Experience: 5+ Years Joining: Immediate / 15 Days Preferred

Must Have Skills

• Python
• Node.js
• Large Language Models (LLM)
• Retrieval-Augmented Generation (RAG)

Good to Have

• React.js or Angular

Job Description

We are looking for a skilled AI Engineer with 5+ years of experience in building intelligent applications using LLM and RAG architectures. The ideal candidate should have strong hands‑on expertise in Python and Node.js, along with experience integrating AI models into scalable production systems.

Key Responsibilities

• Design and develop AI‑powered applications using LLM, RAG, and vector databases.
• Build backend services and APIs using Python and Node.js.
• Implement document ingestion, chunking, embeddings, retrieval, and prompt orchestration pipelines.
• Integrate AI solutions with web applications and enterprise systems.
• Optimize model performance, response quality, latency, and scalability.
• Collaborate with frontend developers (React/Angular) and cross‑functional teams for end‑to‑end delivery.
• Follow best practices for testing, deployment, monitoring, and security of AI applications.

Required Qualifications

• 5+ years of software development experience.
• Strong proficiency in Python and Node.js.
• Hands‑on experience with LLMs (OpenAI, Claude, Gemini, Llama, etc.).
• Experience building RAG‑based applications using vector databases such as Pinecone, Qdrant, Chroma, or FAISS.
• Good understanding of APIs, microservices, and cloud‑native application development.
• Familiarity with prompt engineering, embeddings, and AI application evaluation.

Preferred

• Experience with React.js or Angular.
• Exposure to Docker, Kubernetes, CI/CD, and cloud platforms (AWS/Azure/GCP).