Senior AI Engineer: LLM Apps, Vector DBs & Pipelines

Nuclieos; Lahore; On-site; PKR 2,500,000 - 4,500,000; Full time

Job summary

Nuclieos in Lahore is seeking a Senior AI Engineer to design and deliver LLM applications and agentic systems that automate workflows. You will work across AI engineering and data pipelines, with an emphasis on enabling business stakeholders to understand technical work.

You will build RAG, MCP, and agent orchestration solutions, apply prompt and context engineering, and optimize token usage for performance and security, while maintaining data quality across ETL/ELT pipelines.

Qualifications

• 5+ years in software or AI engineering.
• Practical experience delivering LLM applications and agentic systems.
• Excellent written and spoken English.
• Ability to explain technical concepts to business stakeholders.

Responsibilities

• Deliver LLM applications and agentic AI systems.
• Build RAG, MCP, and agent orchestration solutions.
• Apply prompt and context engineering, execution loops, and security guardrails.
• Optimize token usage and system performance.
• Build and maintain ETL/ELT pipelines, data models, and vector databases, ensuring data quality.
• Communicate progress and risks proactively to stakeholders and cross-functional teams.

Skills

Python

TypeScript

APIs

SQL

ETL/ELT pipelines

Data modeling

Data quality

Vector databases

RAG architecture

Agent orchestration

Prompt engineering

Context engineering

Execution loops

Security guardrails

Token optimization

Clear communication

Cross-team collaboration

Proactive reporting

Tools

APIs

SQL

Vector databases

ETL/ELT pipelines

Job description

Nuclieos in Lahore is seeking a Senior AI Engineer to design and deliver LLM applications and agentic systems that automate workflows. You will work across AI engineering and data pipelines, with an emphasis on enabling business stakeholders to understand technical work.

You will build RAG, MCP, and agent orchestration solutions, apply prompt and context engineering, and optimize token usage for performance and security, while maintaining data quality across ETL/ELT pipelines.