Location: Islamabad, Pakistan

Position: 2

Mode of Work: On-Site

Shift: Night Shift (9pm-6am)

We are seeking a talented and motivated Junior AI Engineer to join our team. The ideal candidate will have expertise working with AI & Data. Additionally, experience with Cloud platforms, data visualization tools & Docker is a strong advantage.

Qualifications:

• 1 to 2 years of professional experience as an AI/Data Engineer or related role.
• Experience building applications with LLMs (OpenAI, Anthropic, Google Gemini, or open-source via Ollama / HuggingFace)
• Hands-on experience with LangGraph and/or LangChain for agentic and multi-step LLM workflows
• Understanding of AI agent architecture: tool calling, state graphs, routing logic, and multi-agent coordination
• Prompt engineering skills: system prompts, few-shot prompting, chain-of-thought, structured output, and prompt versioning
• Short-term vs. long-term memory management for agents: in-context memory, vector store retrieval, and persistent state (Redis, PostgreSQL)
• Strong proficiency in SQL and database management.
• Experience with Python for data processing and automation.
• Understanding of ETL/ELT concepts and data pipeline development.
• Familiarity with relational databases such as PostgreSQL, MySQL, or SQL Server.
• Familiarity with version control systems such as Git.
• Understanding of data warehousing concepts and dimensional modeling.
• Experience with cloud platforms such as AWS, Azure, or Google Cloud Platform is a plus.
• Knowledge of data visualization and reporting tools such as Power BI, Tableau, or Looker is a plus.
• Exposure to Docker and containerized deployments is a plus.
• Understanding of data governance and security best practices.
• Strong analytical and problem-solving skills.
• Good communication and teamwork abilities.

Education:

• Bachelor's degree in Data Science, Computer Science, Software Engineering, or relevant field.

Responsibilities:

• Design and build LLM-powered agents and multi-agent workflows using LangGraph or LangChain.
• Implement session and memory management: short-term context handling, long-term memory via vector stores, and persistent user state.
• Engineer and iterate on system prompts, instruction sets, and few-shot examples to improve model reliability and output quality.
• Manage token budgets and design chunking, summarization, and retrieval strategies for efficient context window usage.
• Integrate LLMs with external tools, databases, REST APIs, and knowledge bases using tool-calling and function calling.
• Implement guardrails, output validation, and error-recovery layers for production AI systems.
• Document agent architectures, prompt versions, memory schemas, and deployment configurations.
• Develop, maintain, and optimize ETL/ELT pipelines for data ingestion, transformation, and loading.
• Design and manage data models, databases, and data warehouses.
• Collect, clean, validate, and process data from multiple sources.
• Monitor data pipelines and troubleshoot data-related issues.
• Ensure data accuracy, consistency, and integrity across systems.
• Collaborate with Data Analysts, Data Scientists, and Software Engineers to support reporting and analytics requirements.
• Create and maintain technical documentation for data workflows and processes.
• Assist in implementing data governance, security, and compliance best practices.
• Optimize database performance and query execution.
• Support the automation of data collection and reporting processes.
• Provide technical support and documentation.

Compensation and Benefits:

• Market Competitive Salary
• Personal and Family Medical Insurance
• Personal Life Insurance
• Parental Medical Insurance
• Personal and Family OPD
• Paid Time-off
• EOBI
• Paid Technical Certifications