Senior GenAI Engineer: LLMs, RAG & Autonomous Agents

Strategic Systems International; Lahore; On-site; PKR 1,800,000 - 2,600,000; Full time

Job summary

Strategic Systems International in Lahore is looking for a GenAI/LLM Engineer with 3+ years of hands-on experience to design and optimize cutting-edge AI solutions. You will work on end-to-end GenAI systems, from prompt pipelines to RAG architectures, integrating APIs, vector stores, and external tools.

You will collaborate across teams to build scalable, reliable AI systems, implement multi-step autonomous agent workflows, and ensure robust performance and debugging.

Qualifications

• 3+ years in AI/ML or software engineering.
• Hands-on experience with end-to-end GenAI/LLM projects.
• Experience with LangChain / LangGraph.
• Understanding of LLMs, prompts, and RAG.
• Familiarity with REST APIs and microservices.
• ML fundamentals knowledge.
• Strong logical reasoning and debugging.

Responsibilities

• Design, develop, and optimize GenAI solutions using LLMs.
• Build prompt engineering pipelines and optimization.
• Develop RAG systems.
• Design multi-step agent workflows with LangChain/LangGraph.
• Build autonomous agents capable of tool use and reasoning.
• Integrate APIs, vector databases, and external tools.
• Debug and improve performance for reliability and scalability.
• Develop and deploy ML models where required.
• Data processing and feature engineering.
• Work with embeddings and vector databases.

Skills

GenAI experience

LLM development

Prompt engineering

RAG architectures

API integration

Debugging skills

Problem solving

Tools

LangChain

LangGraph

Milvus

Pinecone

Weaviate

REST APIs

Job description

Strategic Systems International in Lahore is looking for a GenAI/LLM Engineer with 3+ years of hands-on experience to design and optimize cutting-edge AI solutions. You will work on end-to-end GenAI systems, from prompt pipelines to RAG architectures, integrating APIs, vector stores, and external tools.

You will collaborate across teams to build scalable, reliable AI systems, implement multi-step autonomous agent workflows, and ensure robust performance and debugging.