Data Analyst – Data Engineering & LLM Integration (Mid-Level)

Inspurate Business Services is seeking a technically skilled Data Analyst with expertise in Data Engineering and Large Language Models (LLMs) to join our expanding technology and AI development team based in Karachi. This role goes beyond traditional data analysis and reporting, requiring a blend of analytical thinking and software engineering capabilities. The ideal candidate will work with both structured and unstructured data to support AI-powered applications, leveraging tools such as SQL, Python, data pipelines, APIs, and LLM workflows. You will contribute to projects involving data analytics, automation, LLM integration, and AI-driven business solutions, collaborating closely with engineers to build scalable, production-ready features.

Key Responsibilities

Data Analysis and Reporting:
- Analyze structured and unstructured datasets to uncover trends, patterns, and actionable insights.
- Develop and maintain reports, dashboards, and data visualizations.
- Write and optimize SQL queries for data extraction, transformation, and analysis.
- Utilize Python, pandas, Excel, and business intelligence tools effectively.
- Ensure data quality, consistency, and accuracy through validation processes.

Data Engineering and Automation:
- Design, develop, and maintain robust data pipelines and reusable Python scripts.
- Build workflows for data transformation and preprocessing.
- Integrate data from various sources including databases, APIs, and spreadsheets.
- Automate repetitive data collection, processing, and reporting tasks.
- Implement maintainable solutions with proper error handling, logging, and documentation.
- Collaborate with software developers to embed data workflows into applications and backend services.

LLM and AI Integration:
- Work with Large Language Models such as OpenAI GPT, Claude, Gemini, and open-source alternatives.
- Develop and test prompt-based workflows for tasks like data extraction, summarization, classification, and insight generation.
- Support Retrieval-Augmented Generation (RAG) implementations and document processing pipelines.
- Prepare, clean, and structure datasets for LLM-powered applications.
- Evaluate LLM outputs for accuracy, consistency, and reliability.
- Integrate LLM APIs into Python-based workflows and collaborate with AI engineers to enhance model inputs and outputs.

Required Qualifications
- 2 to 4 years of relevant experience in data analytics, analytics engineering, data engineering, or related technical roles.
- Strong proficiency in SQL, including complex joins, aggregations, subqueries, and query optimization.
- Expertise in Python, especially with pandas and data processing libraries.
- Experience building reusable scripts, automated workflows, or data pipelines.
- Practical knowledge of LLMs through API usage, prompt engineering, RAG, or model evaluation.
- Familiarity with REST APIs, JSON, and data integration techniques.
- Competence in Excel or Google Sheets for data analysis.
- Working knowledge of at least one BI platform such as Power BI, Tableau, or Looker.
- Solid understanding of data cleaning, validation, transformation, and reporting processes.
- Ability to write clean, maintainable, and well-documented code.
- Strong analytical thinking and problem-solving skills.

Preferred Qualifications and Benefits
- Experience with vector databases like Chroma, FAISS, Pinecone, or Qdrant.
- Understanding of embeddings, semantic search, and RAG architectures.
- Familiarity with LLM frameworks such as LangChain or LlamaIndex.
- Experience with relational databases including PostgreSQL or MySQL.
- Knowledge of Git and collaborative software development workflows.
- Exposure to cloud platforms such as AWS, Azure, or Google Cloud.
- Experience with ETL/ELT processes and workflow orchestration.
- Familiarity with Docker, scheduled jobs, or deployment pipelines.
- Previous involvement in supporting AI-powered products or analytics platforms.

We value candidates who can seamlessly transition between data analysis and engineering tasks, understand the limitations of LLMs, and emphasize data accuracy and maintainability. The ability to independently troubleshoot and collaborate effectively with software developers and AI engineers is essential. This is a full-time, on-site position located in DHA Phase 1, Karachi, with a Monday to Friday work schedule.

Applicants are encouraged to submit their updated CV along with links to GitHub profiles, portfolios, or relevant projects demonstrating SQL and Python data processing, automated workflows, LLM integrations, and data visualizations. Shortlisted candidates may be invited to complete a technical assessment covering SQL, Python, data processing, and LLM integration.

Join Inspurate Business Services to contribute to the development of reliable data infrastructure and innovative AI-powered solutions. The starting salary for this role is Rs100,000 per month.