AI Engineer - LLM, RAG & Automation Systems

Job Description

We are looking for a highly motivated AI Engineer with strong hands-on experience in LLM systems, RAG pipelines, and back-end development.You will be responsible for building production-ready AI applications, focusing on performance, scalability, and real business impact.

This role is ideal for candidates who already have experience working with:

● Agent-based systems

● Vector databases

● AI deployment pipelines

2. Key Responsibilities

A. AI Systems Development (40%)

● Design and implement AI agents using:

○ LangChain / LangGraph

● Build and optimize RAG pipelines:

○ Vector databases (Qdrant or similar)

○ Semantic search optimization

● Fine-tune and integrate LLMs:

○ OpenAI, Qwen, Gemma, Llama

B. Backend Development (25%)

● Develop scalable backend services using:

○ Python (FastAPI)

● Improve:

○ System performance

○ API response time

○ Concurrency handling

C. Data Engineering (15%)

● Build data pipelines:

○ Web scraping (Selenium, BeautifulSoup)

○ Data cleaning & structuring

● Prepare datasets for:

○ AI training

○ Knowledge base systems

D. Cloud & Deployment (10%)

● Deploy systems on:

○ Google Cloud Platform (GCP)

○ Linux environments

● Manage:

○ Hosting

○ Scaling

○ Monitoring

E. Automation & Integration (10%)

● Build automation workflows using:

○ n8n / Zapier / Make

● Integrate AI into:

○ Business tools

○ SaaS platforms

Selection Criteria

Hard Skills

● Strong experience with:

○ LangChain / LangGraph / RAG

○ Python (FastAPI)

● Knowledge of:

○ Vector databases (Qdrant, Pinecone…)

○ LLM fine-tuning (LoRA / QLoRA is a plus)

Google Experience (Strong Advantage)

● Experience with:

○ Google Cloud Platform (GCP)

○ Google Developer Groups (GDG)

○ DevFest / Google I/O / tech community

Candidates with Google ecosystem exposure or leadership will be prioritized.

How To Apply

Please email your CV, references and qualifications.