LangChain and Python Developer – Singapore
Posted
Summary
Builds and deploys LLM-powered applications in Python using LangChain: RAG pipelines (ingestion, chunking, embeddings, vector DB indexing), prompt engineering and tuning with models like OpenAI, Claude, and Llama, plus production deployment and evaluation of output quality.
A LangChain and Python Developer specializes in building applications leveraging Large Language Models (LLMs) and the LangChain framework. This role focuses on developing, optimizing, and deploying sophisticated RAG (Retrieval-Augmented Generation) systems and generative AI applications.
Key Responsibilities- LLM Application Development: Design and implement end-to-end applications using Python and the LangChain framework to orchestrate complex LLM calls, agents, chains, and custom tools.
- RAG System Engineering: Develop and optimize data pipelines for ingestion, chunking, embedding generation, and vector database indexing to improve RAG performance and context relevance.
- Model Tuning: Work with various LLMs (e.g., OpenAI, Claude, Llama) and implement prompt engineering techniques and fine-tuning strategies to achieve desired application behavior.
- Deployment and Scalability: Deploy and maintain LLM applications in a production environment, ensuring high performance, low latency, and adherence to cost constraints.
- Evaluation: Develop metrics and evaluation frameworks for testing and monitoring the quality and reliability of LLM outputs.
- Bachelor's degree in Computer Science, Data Science, or a related field.
- 3+ years of professional experience in Python development.
- 1+ years of hands-on experience developing with LangChain or similar LLM orchestration frameworks.
- Experience with vector databases (e.g., Pinecone, Chroma, Milvus) and embedding models.
- Solid understanding of cloud platforms (AWS, Azure, or GCP) for application deployment.