Description

You will build and deploy GenAI applications, autonomous agents, and scalable RAG services.

This role is on-site.

Responsibilities

• Develop GenAI applications using foundation models, GraphRAG, and agentic frameworks.
• Design and deploy RAG services and scalable REST APIs using Python (FastAPI) and cloud platforms.
• Implement LLM evaluation frameworks (Ragas, LangSmith) to measure relevance, groundedness, and hallucination.
• Apply LLMOps/MLOps practices including CI/CD, prompt management, and monitoring of latency and cost.
• Build systems leveraging embeddings, knowledge graphs, and ontology extraction at scale.

Required Skills

• 5+ years of experience in software engineering or AI development.
• Strong proficiency in Python and FastAPI for building REST APIs.
• Experience with Docker and containerization.
• Hands-on experience with CI/CD pipelines.
• Proficiency in at least one major cloud platform: AWS, Azure, or GCP.
• Practical experience with RAG architectures and MLOps.
• Understanding of LLM evaluation metrics and tools.

Preferred Skills

• Experience with GraphRAG and advanced agentic architectures.
• Knowledge of knowledge graphs and ontology extraction.
• Experience mentoring developers and collaborating across engineering teams.

Bachelor's degree

Key Skills

Education

Bachelor's degree