AI / ML Engineer - RAG Specialist

They are building Better AI a next-generation healthcare assistant that delivers truthful, scientifically cited, and actionable health insights to consumers and doctors. Starting with a web app (soon expanding to iOS & Android), our vision is to evolve to be a personalized health companion that integrates with users health apps and provides comprehensive support.

The Job :

As an AI / ML Engineer - RAG Specialist, you will be a core member of our founding team, designing and deploying production-grade RAG (Retrieval-Augmented Generation) systems and semantic retrieval pipelines for our healthcare assistant. Youll be working at the intersection of AI, healthcare, and real-world impactbuilding scalable, accurate, and trustworthy systems that deliver scientifically cited insights to consumers and doctors.

This role is ideal for an engineer with strong expertise in LLMs, data retrieval systems, and a deep passion for applying AI to solve meaningful problems.

Key Responsibilities :

• Design, develop, and deploy production-grade RAG pipelines (Graph RAG, Neo4j, vector databases).
• Build and optimize LLM-based solutions using frameworks like LangChain, LlamaIndex, and Hugging Face Transformers.
• Create and manage scalable data pipelines for structured and unstructured healthcare data.
• Fine-tune LLMs for domain-specific accuracy, reasoning, and reliability.
• Deploy ML models on AWS SageMaker / Bedrock, build APIs / microservices for production, and ensure scalability.
• Collaborate in an agile startup environment with a high sense of ownership and end-to-end responsibility.

Ideal Candidate :

• You hold a Bachelors or Masters degree in Computer Science, with specialized coursework in AI / ML engineering.
• You have 2+ years of hands-on experience in Python and building production-grade RAG applications, preferably including Graph RAG.
• Understanding of retrieval metrics, generation quality assessment, and hallucination detection. Ability to design and implement automated evaluation pipelines for continuous quality monitoring.
• You have gained strong exposure to vector databases (FAISS, Pinecone, Weaviate, ChromaDB) and graph stores (Neo4j).
• Proficiency with LLMs (GPT, Llama, Claude, etc.) and frameworks like LangChain, LlamaIndex, Hugging Face is required.
• You possess a good hold of embeddings, semantic search, and information retrieval systems.
• You are familiar with MLOps practices (deployment, monitoring, optimization)
• You thrive in fast-paced, AI-first environments and are driven to perform in remote teams.

(ref : hirist.tech)