AI Engineer (LLM + LangChain + RAG) at FlexiSAF Edusoft Limited

We are seeking an AI Engineer to build innovative LLM-powered applications using tools like LangChain, RAG, and vector databases. We're looking for a smart, passionate engineer eager to solve real-world problems with AI. Experience with Spring is a plus. Perfect for early-career talents ready to make an impact.
 

• Minimum Qualification : High School (S.S.C.E)
• Experience Level : Entry level
• Experience Length : 2 years
• Working Hours : Full Time

Responsibilities

• Design and build AI-powered applications using LLMs, LangChain, and RAG techniques.
• Implement intelligent workflows that integrate structured and unstructured data sources.
• Create conversational agents and retrieval systems using embedding, vector stores, and APIs.
• Collaborate with frontend/backend engineers to bring LLM features into web or mobile applications.
• Keep up with the fast-moving world of generative AI and experiment with bleeding-edge tools.
• Apply enterprise frameworks like Spring Boot to wrap or scale LLM services.

Typically, we will review applications and respond to only qualified candidates; interested candidates are advised to apply as soon as possible as we will close applications once we receive sufficient amount of applications.

Requirements

• Strong understanding of how LLMs work and how to fine-tune or chain them using frameworks like LangChain or LLamaIndex.
• Experience with Python (preferred), especially in AI/ML development.
• Ability to build, test, and deploy LLM features in real-world applications.
• Familiarity with RAG pipelines, vector databases (e.g. FAISS, Pinecone), and embedding techniques.
• Comfort working with APIs and integrating AI services.
• Curiosity, energy, and a strong desire to learn and grow.
• Experience with Java and Spring Boot for building enterprise-grade services.