Description

You will lead the design and production of Generative AI and Machine Learning systems, focusing on RAG architectures and enterprise-scale model integration.

This role is on-site.

Responsibilities

• Architect and deploy RAG pipelines using LangGraph, Langfuse, and vector databases.
• Build and maintain microservices and REST APIs orchestrated via Kubernetes and Helm.
• Implement model evaluation frameworks like RAGAS and DeepEval for continuous quality assurance.
• Leverage logs, telemetry, and enterprise datasets to refine LLM, Transformer, and BERT models.
• Drive deep technical discussions and whiteboarding sessions to resolve complex engineering challenges.

Required Skills

• 12+ years of production experience in Machine Learning and Generative AI.
• Deep expertise in RAG patterns, Semantic Search, and Vector Databases.
• Proficiency with LangGraph and Langfuse for workflow orchestration and observability.
• Strong background in LLMs, Transformers, BERT, and Rasa.
• Experience with Kubernetes, Helm, Microservices, and REST API development.
• Bachelor’s or Master’s degree in Computer Science, Data Science, or a related field.

Key Skills

Education

Bachelor's or Master's degrees