Full-Stack & Agentic AI Engineer

VaporVM; Lahore; On-site; PKR 2,500,000 - 5,500,000; Full time

Job summary

VaporVM is seeking an AI Engineer with a strong full-stack background to design, develop, and deploy production-grade AI applications and agentic systems in Lahore. The role combines hands-on development with practical experience in LLMs, RAG, AI agents, and orchestration frameworks.

Responsibilities include building scalable full-stack apps, RAG pipelines, AI agents, and secure APIs, while optimizing performance, latency, and cost.

Qualifications

• 5+ years of software/full-stack engineering experience.
• Proficient in Python and/or Node.js.
• Frontend expertise with React/Next.js or equivalents.
• Backend/API development using REST APIs, microservices, and databases.
• Practical experience with LLMs and Generative AI.
• Strong understanding of RAG, embeddings, vector databases, semantic search, retrieval pipelines.
• Experience with AI agent development and orchestration frameworks.
• Hands-on with LLM APIs, tool calling, prompt engineering, and structured outputs.
• Data pipelines, ETL/ELT, ingestion and processing.
• Docker, Kubernetes, CI/CD, Git, and cloud platforms.
• Strong software architecture, security, scalability, and production deployment.

Responsibilities

• Design and develop AI-powered applications and agentic solutions using modern LLM tech.
• Build scalable full-stack applications with backend APIs and frontend interfaces.
• Develop RAG pipelines using vector databases, embeddings, and retrieval tech.
• Build and orchestrate AI agents for reasoning, tool use, and multi-step workflows.
• Work with LLMs, prompt engineering, context management, and function/tool calling.
• Integrate AI models via APIs and frameworks such as LangChain, LangGraph, or equivalents.
• Design data pipelines for ingestion, transformation, processing, indexing, and retrieval.
• Develop secure, scalable APIs and microservices for enterprise integration.
• Deploy and operate AI solutions across cloud and containerized environments.
• Optimize AI applications for performance, scalability, reliability, latency and cost.
• Implement monitoring, logging, and observability for LLM and agentic apps.
• Collaborate with product, engineering, data, and business teams to deliver production-ready AI solutions.

Skills

Python

Node.js

React

Next.js

REST APIs

Microservices

LLMs

RAG

AI agents

Docker

Kubernetes

CI/CD

Cloud platforms

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Job description

We are looking for a strong AI Engineer with a solid full-stack software engineering background to design, develop, and deploy production‑grade AI applications and intelligent agentic systems.

The ideal candidate should combine hands‑on full‑stack development expertise with practical experience in LLMs, RAG, AI agents, orchestration frameworks, APIs, and data pipelines. Candidates who have actually built and deployed AI agents in production will be strongly preferred.

Key Responsibilities

• Design and develop AI‑powered applications and agentic solutions using modern LLM technologies.
• Build scalable full‑stack applications, including backend APIs, services, databases, and frontend interfaces.
• Develop RAG (Retrieval‑Augmented Generation) pipelines using vector databases, embeddings, document processing, and retrieval techniques.
• Build and orchestrate AI agents capable of reasoning, tool usage, task execution, and multi‑step workflows.
• Work with LLMs, prompt engineering, context management, function/tool calling, and agent orchestration.
• Integrate AI models and services through APIs and frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent.
• Design and implement data pipelines for ingestion, transformation, processing, indexing, and retrieval.
• Develop secure and scalable APIs and microservices to integrate AI capabilities with enterprise applications.
• Deploy and operate AI solutions across cloud and containerized environments.
• Optimize AI applications for performance, scalability, reliability, latency, and cost.
• Implement evaluation, monitoring, logging, and observability for LLM and agentic applications.
• Collaborate with product, engineering, data, and business teams to translate requirements into production‑ready AI solutions.

Required Skills & Experience

• 5+ years of software/full‑stack engineering experience with strong hands‑on development expertise.
• Strong proficiency in Python and/or Node.js.
• Solid experience with modern frontend technologies such as React, Next.js, or equivalent.
• Strong backend/API development experience using REST APIs, microservices, and databases.
• Practical experience building applications using LLMs and Generative AI.
• Strong understanding of RAG, embeddings, vector databases, semantic search, and retrieval pipelines.
• Experience with AI agent development and orchestration frameworks.
• Hands‑on experience with LLM APIs, tool/function calling, prompt engineering, and structured outputs.
• Experience with data pipelines, ETL/ELT, data ingestion, and data processing is highly desirable.
• Experience with Docker, Kubernetes, CI/CD, Git, and cloud platforms.
• Strong understanding of software architecture, security, scalability, and production deployment.

Strongly Preferred

• Proven experience building and deploying AI agents into production.
• Experience with multi‑agent architectures and agentic workflows.
• Experience with LangGraph, LangChain, LlamaIndex, Semantic Kernel, or similar frameworks.
• Experience with Azure AI, AWS Bedrock, Google Vertex AI, OpenAI, or equivalent platforms.
• Experience with Kafka, Spark, Airflow, Databricks, or similar data technologies.
• Experience implementing LLM evaluation, observability, guardrails, and AI security.