AI Engineer

Big Entities; Lahore; On-site; PKR 1,800,000 - 2,500,000; Full time

Job summary

Big Entities is building an AI-driven no-code platform in Lahore. As an AI Engineer, you will design systems that translate user ideas into production-ready UI, backend logic and databases, while exploring self-hosted LLMs and on-premise deployments.

You will work on multi-step AI agents, code generation, and integration of AI features across frontend and backend teams. Strong Python/Go/TypeScript skills and experience with LLMs are essential.

Qualifications

• Proficient in Python, Go and/or TypeScript with production experience.
• Hands-on experience building apps using LLM APIs.
• Familiar with LangChain/LangGraph or similar toolchains.

Responsibilities

• Design and build LLM-powered pipelines translating natural-language specs into code, data models and APIs.
• Develop multi-step AI agents for planning, code generation and bug fixing.
• Create design-to-code features using vision-based and multimodal models.
• Manage prompts, context, and retrieval to follow coding standards.
• Evaluate and improve code generation quality, latency and cost across providers.
• Collaborate with frontend, backend, and product teams to embed AI features.

Skills

Python

GO

TypeScript

LLM APIs

LangChain

LangGraph

LlamaIndex

Vector databases

AST parsing

Code analysis

Compilers

vLLM

Ollama

GPU basics

Code generation

Tool calling

AWS

Azure

Job description

AI Engineer

Location: Onsite DHA Phase 3 Lahore

Timings: 1 PM – 10 PM

Experience: 2 - 4 years

About the Role

We’re building an AI-driven no-code platform that turns ideas, prompts and designs into production-ready web and mobile applications. As an AI Engineer, you’ll design and ship the intelligence behind it: the systems that understand what users want and generate working UI, backend logic and databases. You’ll also research and build alternatives to frontier model APIs, including self-hosted and on-premise LLMs.

Key Responsibilities

Engineering

• Design and build LLM-powered pipelines that convert natural-language requirements into application code, data models and APIs.
• Develop multi-step AI agents for planning, code generation, self-correction and automated bug fixing.
• Build design-to-code features (Figma, XD, wireframes) using vision and multimodal models.
• Engineer prompts, context management and retrieval (RAG) so outputs follow our component library and coding standards.
• Create evaluation frameworks to measure generated code quality, accuracy and reliability, and improve them continuously.
• Optimize model latency, cost and token usage across providers (OpenAI, Anthropic, open-source).
• Work with frontend, backend and product teams to integrate AI features into the builder experience.

Research & Exploration

• Research and evaluate alternatives to frontier model APIs, including open-source LLMs (Llama, Qwen, Mistral, DeepSeek) for code generation and reasoning tasks.
• Design and run on-premise and private-cloud LLM deployments for data privacy, cost control and enterprise customers.
• Benchmark self-hosted models against frontier models on accuracy, latency and cost, and recommend where each fits in the platform.
• Explore model optimization techniques such as quantization, distillation and fine-tuning (LoRA/QLoRA) to run capable models on limited hardware.
• Prototype hybrid routing that sends simple tasks to smaller in-house models and complex tasks to frontier models.
• Stay current with AI research and turn promising ideas into working prototypes and internal tech notes.

Required Skills

• Strong Python, GO and/or TypeScript skills.
• Hands-on experience building production applications with LLM APIs.
• Experience with agent frameworks (LangChain, LangGraph, LlamaIndex or similar) and vector databases.
• Experience with AST parsing, code analysis or compilers.
• Experience serving open-source LLMs with tools like vLLM or Ollama.
• Understanding of GPU infrastructure, model memory requirements and inference scaling.
• Experience with structured outputs, function/tool calling and code generation.
• Familiarity with cloud deployment (AWS or Azure) and Docker.

Nice to Have

• Fine-tuning or evaluating open-source models.
• Prior work on no-code, low-code or developer-tool products.
• Knowledge of MCP or tool-integration protocols.