Job Description

About the Role

We are hiring an AI Engineer with strong experience in large language models, retrieval systems, knowledge graphs, and automation workflows. The engineer will build production-ready AI systems that retrieve information, process documents, trigger automated actions, and integrate with external tools and APIs.
This position is suited for someone who understands both AI architecture and software engineering and can deliver solutions from design to deployment.

ResponsibilitiesLLM Engineering

Design and optimize Retrieval-Augmented Generation (RAG) systems. Build knowledge graphs and perform entity and relationship extraction. Fine-tune LLMs using LoRA, QLoRA, and instruction tuning methods. Evaluate model outputs using RAG evaluation metrics such as RAGAS.

AI Agents and Automation

Build multi-step AI agents using frameworks such as LangChain or LangGraph. Create automation workflows including email automation, marketing automation, and document processing. Integrate third-party tools and APIs into AI systems.

Backend and Infrastructure

Develop backend services using FastAPI or Django. Build REST APIs for AI features. Deploy AI models on cloud GPU platforms such as AWS, GCP, or Nebius. Manage vector databases such as FAISS, Pinecone, Chroma, or Weaviate.

MLOps

Deploy and scale LLMs using vLLM or Hugging Face TGI. Set up Docker environments, CI/CD pipelines, and monitoring tools. Build data pipelines for document ingestion and processing.

Required Skills

Strong knowledge of transformers, embeddings, and tokenization. Experience in RAG, Graph-RAG, hybrid retrieval, and metadata-based retrieval. Proficiency in Python. Experience with FastAPI, Flask, or Django. Experience with Docker, Git, and CI/CD. Cloud deployment experience with AWS, GCP, Azure, or GPU cloud providers. Experience with vector databases.

Preferred Skills

Knowledge-graph or Neo4j experience. Experience with tools like Zapier, n8n, or Make for automation. Understanding of email marketing automation. Experience with React or Next.js. Experience with multi-agent AI systems.

What We're Looking For

We are seeking someone who can build end-to-end AI systems, understands production-level scalability, and can design workflows involving agents, graph-based retrieval, and automation. The ideal candidate stays updated on current LLM architectures and best practices.

Job Types: Full-time, Permanent

Pay: From ?20,000.00 per month

Expected Start Date: 10/12/2025