Artificial Intelligence AI Engineer (Generative AI & LLMs) Park View City Lahore

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

Job summary

Buggcy is seeking an AI Engineer to design, build, and deploy AI-powered applications. The role emphasizes end-to-end AI solutions, including RAG pipelines, agents, and API integrations, with direct sprint involvement.

The candidate will work on scalable backends using FastAPI/Flask, Docker, and cloud platforms, collaborating closely with engineers and product teams to deliver production-ready AI systems.

Qualifications

• 2+ years of professional AI/ML engineering or related software development experience.
• Strong proficiency in Python and hands-on experience with LLMs, Generative AI, and prompt engineering.
• Experience building RAG-based applications and familiarity with AI orchestration frameworks.
• Experience integrating LLM APIs and open-source models; understanding embeddings and vector databases.
• Knowledge of Git, Docker, and cloud deployment; ability to deliver with minimal supervision.

Responsibilities

• Design, develop, and deploy AI-powered applications using LLMs and Generative AI technologies.
• Build and optimize RAG pipelines for document retrieval and QA systems.
• Develop AI agents and multi-agent workflows using LangChain, LangGraph, or CrewAI.
• Integrate LLM APIs from OpenAI, Anthropic Claude, and open-source models.
• Implement prompt engineering, structured outputs, function calling, and tool integrations.
• Work with vector databases like Pinecone, Weaviate, ChromaDB, or FAISS.
• Fine-tune and optimize models for business use cases.
• Develop scalable backend APIs with FastAPI or Flask.
• Deploy AI apps using Docker and cloud platforms (AWS/Azure/GCP).
• Evaluate model performance, latency, and cost.
• Collaborate with engineers and product teams to deliver reliable AI solutions.

Skills

Python

LLMs

Generative AI

RAG

LangChain

LangGraph

CrewAI

LLM APIs

Embeddings

Vector databases

Pinecone

Weaviate

ChromaDB

FAISS

FastAPI

Docker

AWS

Azure

GCP

Git

CI/CD

MLOps

Security

Education

Bachelor's degree in Computer Science, AI, Software Engineering, or related field

Tools

Pinecone

Weaviate

ChromaDB

FAISS

LangChain

LangGraph

CrewAI

OpenAI APIs

Anthropic Claude

Job description

SPEC // Artificial Intelligence — OPEN ROLE

About the opportunity

About the RoleWe are looking for a skilled and passionate AI Engineer to join our team and build intelligent, scalable, and production-ready AI solutions.The ideal candidate should have strong experience in Python, Large Language Models (LLMs), Generative AI, Retrieval-Augmented Generation (RAG), and AI Agents, along with the ability to design, develop, and deploy end-to-end AI applications.

At Buggcy, you are not treated as ticket-taker or outsourced labor. You operate as a core member of high-caliber engineering pods with direct client sprint access, high architectural ownership, and zero layers of unnecessary management.

What you will own

• 01. Key Responsibilities
• 02. Design, develop, and deploy AI-powered applications using LLMs and Generative AI technologies.
• 03. Build and optimize RAG pipelines for intelligent document retrieval and question-answering systems.
• 04. Develop AI agents and multi-agent workflows using frameworks such as LangChain, LangGraph, or CrewAI.
• 05. Integrate LLM APIs, including OpenAI, Anthropic Claude, and open-source models.
• 06. Implement prompt engineering, structured outputs, function calling, and tool integrations.
• 07. Work with vector databases such as Pinecone, Weaviate, ChromaDB, or FAISS.
• 08. Fine-tune and optimize machine learning and language models for specific business use cases.
• 09. Develop scalable backend APIs using FastAPI or Flask.
• 10. Deploy AI applications using Docker and cloud platforms such as AWS, Azure, or GCP.
• 11. Evaluate AI model performance, response accuracy, latency, and cost.
• 12. Collaborate with software engineers and product teams to deliver reliable AI solutions.
• 13. Required Skills & Qualifications
• 14. Bachelor's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field, or equivalent practical experience.
• 15. 2+ years of professional experience in AI/ML engineering or related software development.
• 16. Strong proficiency in Python.
• 17. Hands-on experience with LLMs, Generative AI, and prompt engineering.
• 18. Practical experience building RAG-based applications.
• 19. Familiarity with LangChain, LangGraph, or similar AI orchestration frameworks.
• 20. Experience integrating LLM APIs and working with open-source models.
• 21. Understanding of embeddings, semantic search, and vector databases.
• 23. Knowledge of Git, Docker, and cloud deployment.
• 24. Strong problem-solving skills and the ability to independently deliver AI solutions.
• 25. Nice to Have
• 26. Experience with Hugging Face Transformers, PyTorch, or TensorFlow.
• 27. Knowledge of fine-tuning techniques such as LoRA and QLoRA.
• 28. Experience with agentic AI, MCP (Model Context Protocol), and tool-calling architectures.
• 29. Familiarity with LLM evaluation, observability, and monitoring tools.
• 30. Experience with MLOps, CI/CD, and production AI deployment.
• 31. Understanding of AI security, guardrails, and responsible AI practices.
• 32. What We're Looking For
• 33. We value practical experience over theoretical knowledge.

What we look for

2+ years of professional experience in AI/ML engineering or related software development.

• 01. 2+ years of professional experience in AI/ML engineering or related software development.

Direct Sprint Integration

No middlemen, project account managers, or translation layers. You participate in sprint planning, architectural design reviews, and daily standups directly alongside client technical leads.

AI-Native Workflows

We equip our engineers with world-class AI coding workflows, automated review graphs, and prompt evaluation systems. You spend less time writing boilerplate and more time solving architectural problems.

Every pod is comprised of experienced practitioners. You build alongside engineers who hold themselves to high code standards, thoughtful PR reviews, and meticulous system observability.