LLM Solutions Architect
Xsolla is a video game commerce company that provides a suite of tools and services—including merchant of record payment processing, tax management, fraud prevention, compliance, refunds, dispute management, and end-user support—to help game developers and publishers launch, grow, and monetize their games globally. It serves video game developers, publishers, and studios of all sizes across global and regional markets.
About Xsolla
Xsolla connects the tools, systems, payments, and web shops used by the video games industry, positioning itself as a global merchant of record supporting over 1,000 payment methods and a cumulative audience of 50 million, with transaction fees around 5%. Its services include tax management, fraud monitoring and prevention, global and regional regulatory compliance, refund and dispute management, and end-user payment support. Xsolla's product lineup includes the Xsolla SDK for native in-app payments on side-loaded apps and alternative app stores, a Buy Button enabling link-out purchases from iOS mobile games in the U.S., and Web Shop for building customized, direct-to-consumer game storefronts. The company works with major gaming industry partners and clients such as Mytona, Ubisoft, MARVEL SNAP, and others, and highlights partner success stories, industry events, and its own culture and hiring initiatives on its site.
Skills
About the Role
You will join the Monetization Products team as a builder who shapes strategy and ships real systems. You will drive AI product hypotheses from prototype to production-grade engineering, designing end-to-end agentic architectures and a shared LLM platform layer that product engineering teams can build on and operate independently. You will prototype rapidly to validate ideas, ensure everything you build is observable and documented for handoff, and work closely with Product leadership to shape what AI capabilities get prioritized. You will also select and govern LLM providers, drive cross-team alignment on what 'agent-ready' means, and mentor engineers on LLM integration and production deployment practices.
Requirements
- 5+ years of engineering experience, with at least 2 years designing and deploying LLM-powered systems in production
- Proven track record designing agentic systems: tool-use, function calling, multi-step reasoning, orchestration, and error recovery at production scale
- Experience designing AI systems for engineering team ownership including observability standards, handoff documentation, and runbooks
- Hands-on experience with major LLM APIs (OpenAI, Anthropic, Google Gemini) and at least one open-source model stack
- Experience building RAG pipelines with vector databases and orchestration frameworks (LangChain, LlamaIndex, or custom)
- Strong Python engineering skills for production-grade LLM services
- Demonstrated ability to influence product direction
- Clear communication of architectural trade-offs to engineers and business outcomes to executives
- Background in gaming, payments, or e-commerce is a plus
- Fine-tuning experience (PEFT/LoRA) for domain-specific model adaptation is a plus
- Experience with multi-agent orchestration frameworks (AutoGen, CrewAI, or custom) is a plus
- Familiarity with LLM evaluation frameworks (RAGAS, DeepEval, or custom harnesses) is a plus
- Exposure to EU AI Act, GDPR, or other AI compliance frameworks is a plus
Responsibilities
- Design end-to-end agentic architectures including tool-use schemas, intent parsing, multi-step orchestration, and safety guardrails engineered for long-term ownership by product engineering teams
- Define the multi-modal interface strategy across the product portfolio spanning UI, API, SDK, and agentic natural language
- Design the horizontal LLM platform layer including shared RAG pipelines, prompt libraries, vector search infrastructure, and evaluation frameworks
- Prototype rapidly to validate AI product hypotheses before full engineering investment
- Ensure every system architected comes with observability, documentation, and engineering runbooks for product squad ownership
- Shape product strategy alongside Product leadership by influencing AI capability prioritization and trade-offs
- Select and govern LLM providers and deployment strategies per use case balancing cost, latency, accuracy, and privacy requirements
- Drive alignment across Engineering, Product, and Design on what 'agent-ready' means for each product surface
- Mentor engineers on LLM integration patterns, agent evaluation, and production deployment practices
Benefits
- 100% company-paid medical, dental, and vision plans
- Unlimited Flexible Time Off