Senior GenAI Engineer

N-iX is a global software development service company that helps businesses across the globe create next-generation software products. Founded in 2002, we unite 2,400+ tech-savvy professionals across 40+ countries, working on impactful projects for industry leaders and Fortune 500 companies. Our expertise spans cloud, data, AI/ML, embedded software, IoT, and more, driving digital transformation across finance, manufacturing, telecom, healthcare, and other industries. Join N-iX and become part of a team where your ideas make a real impact.We are looking for a GenAI Engineer to design, build, and optimize generative AI solutions supporting a large-scale document processing and workflow automation platform. This role requires hands-on experience with the latest AI models and LLMs, prompt engineering, model evaluation, RAG architectures, Vertex AI or Gemini models, and cloud-native deployment. You will partner closely with architects and product teams to deliver reliable, responsible, and production-grade AI features.Our client is a global, UK-based financial services and investment banking organization building an AI-powered document processing and automation platform used across multiple divisions within the banking group. The initiative focuses on intelligent data extraction, classification, quality enhancement, and workflow automation using cutting-edge GenAI and cloud technologies.Responsibilities:Design and implement GenAI components including LLM pipelines, RAG flows, prompt templates, and classification/extraction logic.Develop AI-driven features for document understanding, summarization, entity extraction, validation, and workflow automation.Work with Vertex AI & Gemini models for experimentation, fine-tuning, evaluation, and deployment.Create and maintain LLM-as-a-judge evaluation setups to measure model quality, reliability, and accuracy.Optimize costs, latency, and performance of model inference and orchestration.Collaborate with software engineers to integrate AI components into microservices and APIs.Build robust monitoring, observability, and guardrails for LLM behavior, hallucination mitigation, and data safety.Work with stakeholders to understand business needs and translate them into feasible GenAI solutions.Document designs, experiment results, prompts, evaluation metrics, and best practices.Stay current with the rapidly evolving GenAI ecosystem and provide strategic recommendations.Requirements:4+ years of experience in applied Machine Learning, GenAI engineering, or NLP/LLM-focused roles.Hands-on experience with Google Cloud Platform (GCP):Strong experience working with LLMs (OpenAI, Gemini, Claude, Llama, Mistral, etc.).Practical knowledge of:Prompt engineering & prompt optimizationRAG architectures (vector stores, embeddings, retrieval patterns)LLM-as-a-judge evaluation and AI metricsGuardrails, safety layers, and hallucination mitigationProficiency in Python; experience building production-grade AI services.Experience with orchestrating pipelines using Airflow, KubeFlow, Vertex Pipelines, or similar tools.Understanding of microservices & APIs for integrating AI components.Experience working with structured and unstructured data (PDFs, images, text).Advanced English and ability to collaborate with cross-functional teams, including engineering, product, and domain experts. We offer*:Flexible working format - remote, office-based or flexibleA competitive salary and good compensation packagePersonalized career growthProfessional development tools (mentorship program, tech talks and trainings, centers of excellence, and more)Active tech communities with regular knowledge sharingEducation reimbursementMemorable anniversary presentsCorporate events and team buildingsOther location-specific benefits*not applicable for freelancers