Integrated Pipeline consisting of two primary components: Inference and Ingestion. This pipeline operates within the parent runtime environment, designed to streamline and unify data processing and model interaction workflows.

The Ingestion component manages the secure collection, validation, and integration of data from various sources, ensuring high-quality inputs for model training and retrieval processes. The Inference component focuses on generating accurate and contextually grounded responses by leveraging advanced Prompt Engineering and Retrieval-Augmented Generation (RAG) techniques.

Together, these components enable the platform to process requests efficiently via the Platform Services Interface (PSI), while maintaining robust data governance. The Integrated Pipeline enforces strict token-based access control to ensure user data privacy, security, and compliance across all stages of data handling and model interaction.

Requirements:

• Deep understanding of LLM architectures, model selection, prompt engineering, and fine-tuning techniques
• Experience with MLOps / AIOps pipelines and tools
• Proficiency in Python, API design, vector databases, and embedding models
• Knowledge of AI safety, bias mitigation, and data governance principles
• Strong system integration skills across cloud platforms (AWS, Azure, GCP)
• Proven ability to balance innovation and delivery, ensuring GenAI solutions are production-ready and cost-efficient
• Excellent communication and documentation skills for presenting complex AI solutions to stakeholders
• Continuous learning mindset — staying up to date with evolving AI frameworks, model releases, and regulatory trends

Job responsibilities:

• Design, validate, and oversee end-to-end GenAI solutions, including model integration, data pipelines and system orchestration
• Define AI architecture blueprints that align with enterprise standards, scalability and security requirements
• Collaborate with MLOps and developers to integrate LLMs and AI services into business workflows
• Evaluate and select appropriate foundation models, APIs and frameworks (e.g., OpenAI, Azure OpenAI, LangChain)
• Ensure ethical AI principles, data privacy, and compliance with internal and regulatory guidelines
• Lead technical reviews of AI solution designs, prompt engineering strategies and fine-tuning approaches
• Provide technical mentorship to developers on AI integration patterns, observability, and performance tuning
• Partner with product owners and business analysts to translate business problems into GenAI solution designs and prototypes