Описание
N-iX’s client is a global e-commerce leader headquartered in California that connects millions of buyers and sellers across more than 190 markets. The role focuses on building and scaling advanced AI systems for a major ecommerce platform.
Задачи
•Lead the architecture, design, development, and optimization of scalable AI systems using Generative AI, LLMs, retrieval-augmented generation, and agent-based architectures
•Serve as the technical owner or technical lead for high-impact AI initiatives spanning multiple services, systems, teams, or product surfaces
•Design and build agent-led user experiences and backend systems with task decomposition, memory, tool use, dynamic planning, retrieval, workflow orchestration, and multi-agent coordination
•Translate ambiguous business, research, and product opportunities into technical strategies, architecture proposals, implementation plans, milestones, risks, and tradeoffs
•Drive architectural decisions for reliable, maintainable, scalable, cost-effective, observable, and production-ready AI products and platforms
•Contribute directly to complex implementation work across backend services, AI orchestration layers, model integration systems, evaluation frameworks, APIs, data pipelines, and observability tooling
•Partner with Product, Research, Data Engineering, Platform Engineering, and Software Engineering teams to align AI system design with user needs, business goals, platform capabilities, and operational constraints
•Establish and promote technical standards for AI system design, agent architecture, LLM integration, evaluation, experimentation, responsible AI, production monitoring, and operational excellence
•Lead design reviews, architecture reviews, code reviews, technical planning sessions, and production-readiness reviews for complex AI systems
•Mentor and guide engineers through technical problem solving, design feedback, implementation support, code quality improvements, and knowledge sharing
•Advance the internal GenAI platform by contributing reusable components, APIs, frameworks, reference architectures, evaluation patterns, engineering guidelines, and shared services
•Define and improve AI evaluation practices, including offline evaluation, online experimentation, regression testing, model behavior analysis, quality measurement, human feedback loops, and production feedback mechanisms
•Monitor and optimize AI systems in production for latency, quality, scalability, reliability, availability, cost efficiency, safety, and responsible AI use
•Identify technical risks early and drive practical mitigation plans across architecture, implementation, launch, and operations
•Influence technical strategy across teams by aligning engineering decisions with broader organizational goals, platform direction, and long-term scalability
•Stay ahead of advances in AI, LLMs, machine learning engineering, AI agents, retrieval systems, model serving, evaluation tooling, and emerging developer frameworks, applying a pragmatic lens to production adoption
•Drive continuous improvement across design, implementation, evaluation, deployment, monitoring, incident response, and operational processes
Требования
•10+ Years of experience in software engineering, machine learning engineering, AI engineering, distributed systems, or related technical roles
•3+ Years of experience leading complex technical initiatives, setting architecture, mentoring engineers, or providing technical direction across teams
•Deep hands-on engineering skills with the ability to personally design and implement complex production systems
•Strong programming skills in Java, Kotlin, or similar JVM languages
•Experience designing and operating production-grade AI systems, distributed services, APIs, or platform components serving high-volume, real-world user traffic
•Ability to lead technical discussions, evaluate tradeoffs, influence senior partners, and communicate complex AI concepts clearly to technical and non-technical collaborators
•Hands-on experience with Spring Framework, Reactive Programming, Docker and Kubernetes, distributed systems and scalable backend services, REST, GraphQL, gRPC, production monitoring, observability, alerting, incident response, performance optimization, CI/CD, automated testing, deployment practices, and operational support
•Excellent English communication skills
Nice to have: Hands-on experience building agent-led systems, Generative AI system design, retrieval-augmented generation, vector databases, embeddings, semantic search, ranking, knowledge-grounded AI, information retrieval systems, tool-use frameworks, agent orchestration platforms, AI workflow automation, multi-modal model integration, multi-agent system design, internal AI platforms, developer tools, reusable AI services, model-serving infrastructure, evaluation platforms, shared ML infrastructure, high-traffic ecommerce or related environments, responsible AI practices, model governance, safety evaluation, abuse-prevention patterns, production AI monitoring standards, Kafka.
Условия
Remote work is available across the European Union.
