Description

You will build, fine-tune, and deploy LLM-based applications and GenAI services for production environments.

This role is on-site.

Responsibilities

• Develop and fine-tune LLM applications using LangChain, Semantic Kernel, or LlamaIndex.
• Design and implement RAG pipelines using vector databases including Azure Cognitive Search, Pinecone, FAISS, or Weaviate.
• Build chatbots, copilots, and content generation tools using OpenAI, Azure OpenAI, or Hugging Face models.
• Containerize and deploy GenAI services using Docker, FastAPI, and Azure Functions.
• Implement monitoring, evaluation, and prompt optimization workflows to manage model performance in production.

Required Skills

• 5+ years of experience in Data Science, AI/ML, or related fields.
• Strong proficiency in Docker, FastAPI, and Azure Functions.
• Hands-on experience with FAISS and other vector databases.
• Proven track record of developing PoCs or production-grade AI applications.
• Experience with prompt engineering, model selection, and performance tracking.
• Bachelor’s or Master’s degree in Computer Science, Data Science, AI/ML, or a related field.

Preferred Skills

• Experience transforming LLMs, RAG, and Agentic AI systems into secure and scalable platforms.

Key Skills

Education

Bachelor's or Master's degrees