AI/ML Developer

Mô tả công việc

We are seeking an AI/ML Developer to join our team in developing a Retrieval-Augmented Generation (RAG) project using genome data from VCF files (.vcf.gz, .vcf.gz.tbi), deployed on AWS. You will be responsible for building the data processing pipeline, creating a vector store, and integrating a large language model (LLM) to support natural language queries — contributing to an advanced AI solution.

Job Description

• Process and analyze VCF files (.vcf.gz, .vcf.gz.tbi) using pysam or cyvcf2, and normalize the data with VEP or ANNOVAR.
• Generate embeddings and manage the vector store (e.g., FAISS, Pinecone, or Weaviate) for genome data.
• Integrate and optimize the RAG pipeline with LangChain or LlamaIndex, and connect with LLMs (such as OpenAI GPT, LLaMA3, or Mistral).
• Support deployment and testing on AWS (e.g., S3, Lambda).

Yêu cầu công việc

• Minimum 5 years of experience in AI/ML, preferably with RAG projects or genome data processing.
• Proficient in Python with experience handling VCF files and using tools such as pysam or cyvcf2.
• Solid understanding of vector databases (FAISS, Pinecone) and large language models (LLMs).
• Basic knowledge of AWS services (S3, Lambda) is a plus.
• Preference for candidates with experience using LangChain, LlamaIndex, or embedding libraries (e.g., sentence-transformers).

Tại sao bạn sẽ yêu thích làm việc tại đây

• Working time: Monday ~ Friday, 09:00 ~ 18:00
• Receive full benefits for employee according to labor law: annual leave, salary, social insurance
• Opportunities for professional learning and training
• Collaborative and innovative work environment
• Working equipment provided by the company
• Join birthday party, holiday party organized by the company
• Review 1 - 2 times per year