Senior AI Engineer: Production RAG & LLM Systems

Emumba Inc.; Islamabad; On-site; PKR 2,800,000 - 5,200,000; Full time

Job summary

Emumba Inc. in Islamabad is seeking a hands-on Senior AI Engineer who blends strong backend engineering with production Generative AI experience. You will design and ship RAG pipelines, integrate LLMs into real products, and build the backend services that support them.

This is a purely technical IC role, not a managerial one. You’ll lead by example, mentor through code reviews, and own end-to-end technical delivery in a fast-paced environment.

Qualifications

• 5+ years of backend development experience.
• Strong Python and software engineering fundamentals.
• Hands-on production systems experience (not PoCs).
• Experience with RAG, embeddings, retrieval, re-ranking, and vector databases.
• Experience with LangChain, LangGraph, LlamaIndex, AutoGen, or similar frameworks.
• Experience with AWS and cloud-native technologies (Terraform, Kubernetes, Helm, CI/CD).

Responsibilities

• Build and maintain RAG systems including retrieval, re-ranking, embeddings, and vector databases.
• Build AI agent workflows using LangChain, LangGraph, LlamaIndex, AutoGen, or similar tools.
• Develop backend services and APIs using Python, including async programming and multithreading.
• Deploy and manage AI applications using AWS, Kubernetes, Terraform, Helm, and CI/CD.
• Build event-driven systems using Lambda, SQS, SNS, S3, and CloudWatch.
• Work with tools such as API Gateway, LiteLLM, AWS Bedrock, and SageMaker.
• Monitor, debug, test, and improve AI systems running in production.

Skills

Python

Backend development

RAG systems

Production AI

LLMs integration

LangChain

LangGraph

LlamaIndex

AutoGen

Distributed systems

Cloud/AWS

CI/CD

Tools

AWS

Kubernetes

Terraform

Helm

CI/CD pipelines

SageMaker

Bedrock

Lambda

Job description

Emumba Inc. in Islamabad is seeking a hands-on Senior AI Engineer who blends strong backend engineering with production Generative AI experience. You will design and ship RAG pipelines, integrate LLMs into real products, and build the backend services that support them.

This is a purely technical IC role, not a managerial one. You’ll lead by example, mentor through code reviews, and own end-to-end technical delivery in a fast-paced environment.