Were hiring a Middle/Senior Back-end Engineer to build scalable AI/NLP applications for our Japanese technology consulting client. Youll work on LLM integration, RAG pipelines, and enterprise AI solutions that make a real impact.
Key Responsibilities:
- Design & implement pipelines for text processing & retrieval
- Integrate LLMs (GPT, LLaMA, Mistral) with databases, APIs & SaaS systems
- Optimize pipelines for scalability & performance
- Collaborate with PMs & engineers to deliver high-quality products
- Contribute to system architecture & project efficiency
Must-have:
- 3+ years in back-end engineering (Python + SQL)
- Hands-on with vector databases (Pinecone, FAISS, Milvus)
- Experience with RAG pipelines & LLM fine-tuning (LoRA, prompt engineering)
- Knowledge of embeddings, preprocessing, and feature extraction
- Worked with GPT-based or open-source LLMs
- Cloud deployment (AWS/GCP/Azure)
- SaaS integration & hybrid architecture experience
- Ability to customize low-code platforms (Dify, N8N)
- Search/retrieval systems (Elastic, Azure AI Search)
- LLM workflows & orchestration
- MLOps, CI/CD pipelines, monitoring & logging
What we offer:
- Competitive salary & performance-based bonuses (up to 4 months)
- Macbook Pro 16 provided
- Annual salary review & growth opportunities
- Company trip, health check, tea breaks/parties
- Be part of a team building cutting-edge AI/NLP solutions
