Description

About the job

Key Responsibilities

• Design AI solution architectures aligned with business objectives, risk tolerance, and governance requirements.
• Build and deploy LLM workflows, prompt orchestration chains, agent-based solutions, RAG applications, model integrations, classification models, and decision-support capabilities.
• Develop prompt strategies, grounding approaches, tool-calling patterns, guardrails, and fallback mechanisms to improve solution quality and reliability.
• Partner with Data Engineering teams to ensure access to trusted, governed, and high-quality data sources.
• Establish evaluation frameworks, test datasets, scoring rubrics, and model-performance benchmarks.
• Monitor and optimize output quality, relevance, accuracy, consistency, latency, cost efficiency, and hallucination risk.
• Conduct failure-mode analysis and implement continuous improvements to AI systems.
• Collaborate with Quality Engineering, Responsible AI, Security, Privacy, Compliance, and Enterprise Architecture teams.
• Document AI solution behavior, limitations, controls, and operational monitoring requirements.
• Support production readiness through observability, monitoring, model evaluation, and drift detection practices.

Required Qualifications

• Bachelor's degree in Computer Science, Engineering, Data Science, or a related technical field; equivalent experience considered.
• Significant experience in software engineering, machine learning, or AI engineering.
• Hands-on experience building and deploying generative AI and LLM-based applications in production environments.
• Experience with prompt engineering, RAG architectures, AI agents, model evaluation, and operational AI governance.
• Strong understanding of cloud-native architectures, APIs, data platforms, and scalable software systems.
• Knowledge of Responsible AI, security, privacy, and compliance practices.
• Proven ability to work effectively with technical and business stakeholders

Key Skills

Education

Any Graduate