AI Engineer - NLP
Company Description
AJARI TECHNOLOGIES is a technology company focused on an AI-powered learning and workforce development platform. Our solutions are designed for governments, institutions, schools, universities, and large organizations to personalize education, upskill, and transform learning outcomes at a national level. We work to scale education to meet the diverse needs of our clients, ensuring impactful results and continuous improvement.
About the Role
This is a full-time on-site role for an AI Engineer (NLP). We are looking for an AI Engineer (NLP) to build and develop NLP and Large Language Model systems from research to production, with a focus on agentic AI, RAG, and system reliability at scale.
Responsibilities:
Agentic AI & Orchestration:
- Design and develop agentic AI systems with multi-step reasoning, tool calling, and human-in-the-loop workflows.
- Implement stateful workflows using LangGraph or LlamaIndex.
- Integrate various tools and external APIs into LLM workflows.
RAG (Retrieval-Augmented Generation):
- Build end-to-end RAG pipeline: document chunking, embedding generation, retrieval strategies, and reranking.
- Optimize retrieval quality with hybrid search and relevance metrics evaluation.
- Manage vector database for semantic search at scale
Natural Language Processing:
- Apply LLMs for NLP tasks such as summarization, information extraction, text classification, sentiment analysis, and document understanding.
- Build NLP solutions for specific use-cases such as question answering, semantic search, and content generation.
Must Have:
- Experience building agentic AI-based systems using LangGraph or LlamaIndex.
- Understand function calling patterns and integrating external APIs into LLM workflows.
- Have expertise in Retrieval-Augmented Generation (RAG), including document chunking, embeddings, retrieval, and reranking.
- Proficient in using vector databases for semantic search.
- Practical experience applying LLMs for summarization, information extraction, text classification, and document understanding.
Nice to Have:
- Prompt engineering skills and context window optimization.
- Experience with LLM evaluation frameworks and quality metrics.
- Ability to design production-grade APIs.
- Experience using asynchronous Python for scalable LLM applications.
- Experience with multimodal (text and vision).
- Experience implementing WebSocket and Server-Sent Events for streaming responses.
Tech Stack:
- Python
- PyTorch / TensorFlow
- Hugging Face
- LangGraph
- LlamaIndex
- FastAPI
- WebSocket / SSE
- Qdrant
- vLLM
- Git
- Redis
- PostgreSQL / MongoDB
