GenAI/RAG Senior Engineer Zain

Build production-grade GenAI solutions including RAG pipelines, prompt engineering, agent workflows, and LLM orchestration

Implement vector databases, embedding models, retrieval systems, and context management for RAG architectures

Develop and optimize prompts, chains, and agent workflows for business use cases

Conduct model evaluation, testing, and optimization for quality, latency, cost, and safety

Establish GenAI engineering best practices including code standards, testing frameworks, and deployment patterns

Integrate GenAI solutions with enterprise systems, APIs, and data sources

Implement monitoring, logging, and observability for production GenAI systems

Provide technical mentorship and code reviews for junior AI engineers

Partner with Data Engineer on data pipelines and feature stores for GenAI use cases

Capture and document reusable patterns, accelerators, and lessons learned

KPIs can include but are not limited to:

Solution delivery: number of GenAI use cases successfully deployed to production.

Quality metrics: accuracy, relevance, and safety of GenAI outputs meeting business requirements

Performance optimization: latency and cost efficiency of deployed GenAI solutions

Code quality: peer review ratings and technical debt metrics