AI Engineer (Vector Databases & RAG)

Overview

Location: Remote

Type: Contract

Experience Level: Mid-Senior

Tech Stack: Milvus, FAISS, Weaviate, Open Source LLMs, LangChain, PyTorch

We’re looking for an AI Engineer specializing in vector databases and RAG architectures to optimize our multi-modal AI retrieval system. You’ll work with Milvus, FAISS, Weaviate, and open-source LLMs to develop high-performance search and retrieval pipelines that power real-time medical education.

About Us

At MAI, our mission is ambitious: to create machine-readable representations of the human body, propelling next-generation medical AI forward and unlocking the potential of precision medicine for every individual. We are on the lookout for self-reliant team members who thrive in a dynamic environment and are committed to making an impact. We need go-getters who are ready to dive in and contribute to groundbreaking work.

Your Role

As an AI Engineer, you will:

• Develop a high-performance RAG pipeline leveraging vector databases for retrieving high dimensional content.
• Optimize similarity search algorithms (Milvus, FAISS, Weaviate) for lightning-fast, accurate retrieval.
• Fine-tune and deploy open-source LLMs (LLaMA, Mistral, Falcon) to generate medical AI explanations.
• Scale and optimize AI inference pipelines using distributed computing (Kubernetes, Ray, etc.).
• Collaborate with medical experts & data scientists to validate AI-generated outputs for accuracy and compliance.

Key Qualifications

• Strong experience with vector databases (Milvus, FAISS, Weaviate, Annoy).
• Expertise in retrieval-augmented generation (RAG) and semantic search for medical data.
• Hands-on experience fine-tuning and deploying open-source LLMs (LLaMA, Falcon, Mistral).
• Strong background in multimodal AI, handling text and medical imaging data (DICOM, NIfTI).
• Proficiency in Python, with experience in LangChain, PyTorch, Hugging Face Transformers, TensorFlow.
• Knowledge of cloud-based ML deployment (AWS & GCP) and scalable AI architectures.
• Experience with LLM embeddings (OpenAI, Cohere, SentenceTransformers).

Nice to Have

• Background in healthcare AI or biomedical NLP.
• Familiarity with medical knowledge graphs & ontologies (UMLS, SNOMED, RadGraph).
• Understanding of medical data privacy standards (HIPAA, GDPR).

How to Apply?

Send your resume, portfolio, and GitHub (if applicable) to jobs@mai.ai with the subject “AI Engineer – Vector Databases & RAG”.

Job Type: Contractual / Temporary
Contract length: 12 months