About the role
Responsibilities:
- Lead end-to-end design and delivery of production-grade AI/ML solutions including RAG pipelines, LLM-based applications, and extraction systems.
- Architect and develop robust, scalable AI/ML services in Python with a focus on reliability and production-grade performance.
- Develop and optimise AI-driven extraction workflows using document parsing, chunking, embeddings, RAG, and LLM-based extraction methods.
- Deploy and scale AI models on AWS and Azure (SageMaker, Bedrock, Azure AI Foundry) with seamless integration into data pipelines.
- Build and maintain CI/CD pipelines for AI model deployment using GitHub Actions, Azure DevOps, Docker, and Kubernetes.
- Define and implement evaluation frameworks (precision, recall, F1, field-level accuracy) and maintain code quality through reviews and testing.
- Partner with Product, Data Engineering, and Platform teams to translate business requirements into scalable AI solutions.
- Mentor team members and share knowledge to elevate overall team capability.
- Continuously research and apply advancements in NLP, LLMs, and extraction techniques.
- Contribute to efficient development cycles following Agile practices and drive automation across the AI delivery pipeline.