Description

You will design and implement generative AI solutions and large language model architectures.

This role is on-site.

Responsibilities

• Develop and deploy RAG systems and knowledge bases compatible with multiple LLM architectures.
• Implement data vectorization techniques for structured and unstructured datasets.
• Build backend APIs using Java, Node.js, or Python frameworks.
• Optimize SQL databases and data models for efficient querying and movement.
• Manage model deployment using cloud platforms and containerization technologies.

Required Skills

• 5+ years of experience in AI/ML development with a focus on generative models and NLP.
• Extensive experience with LLM architectures including Claude 3.5 Sonnet, LLaMA, and GPT series.
• Proficiency in Python, Java, and Node.js.
• Hands-on experience with RAG systems and vector databases like Faiss or Pinecone.
• Knowledge of embedding models such as BERT or Titan.
• Experience with cloud platforms including AWS, GCP, or Azure.
• Strong backend development skills in Spring Boot, Express.js, Django, or Flask.
• Solid understanding of software architecture, design patterns, and APIs.
• Competency in SQL, data modeling, and ORM concepts.

Preferred Skills

• Experience with containerization technologies.

Key Skills

Education

Any Graduate