Senior Full-Stack Engineer – GenAI

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Design and enhance production-grade LLM applications and agentic workflows utilizing NestJS, XState v5, and the OpenAI SDK.

• Create and oversee the conversation-machine infrastructure, which includes guard/action registries, flow validation with AJV, database-driven flow configurations, and design-time tools within the Epicenter admin.

• Develop and advance the AI systems powering the Epic Support Assistant, a player-facing support chatbot, as well as the Agent Support Assistant, the AI copilot utilized by customer support agents.

• Integrate with MCP servers to facilitate tool usage and agentic behaviors.

• Assess, benchmark, and optimize models across OpenAI, Gemini, Anthropic, and future providers; make model selection decisions that balance quality, latency, throughput, reliability, and cost.

• Diagnose production LLM issues such as hallucinations, retrieval failures, prompt regressions, model drift, token inefficiencies, latency bottlenecks, and provider outages.

• Develop resilience mechanisms including retries, fallback routing, caching, streaming, rate limiting, and provider routing.

• Instrument and optimize model quality using Langfuse tracing, evaluations, prompt management, evaluation datasets, A/B testing, prompt versioning, and production telemetry.

• Manage asynchronous workloads through BullMQ and handle caching with Redis.

• Oversee PostgreSQL persistence management via Kysely.

⛳️ Requirements

• Demonstrated experience in building and operating production LLM-powered systems comparable to chatbots, AI assistants, agent copilots, RAG systems, or LLM orchestration platforms.

• Proficient in TypeScript and Node.js engineering; fluent in TypeScript strict mode.

• Experienced in production AI, including prompt engineering, RAG pipelines, agent design, tool calling, model evaluation, observability, and failure-mode analysis; have delivered AI features rather than just prototypes.

• Full-stack expertise across NestJS APIs, React UIs, databases, infrastructure, and production operations.

• Capability to evaluate trade-offs between model quality, latency, reliability, throughput, and cost.

• Proficient in troubleshooting AI systems across prompts, retrieval pipelines, model configuration, infrastructure, and application code.

• Possess state machine thinking; experience with XState or similar frameworks is a strong indicator.

• Solid grasp of REST API design, asynchronous patterns such as queues and events, and caching strategies.

• Strong testing culture that encompasses unit, integration, and contract tests.

• Familiarity with operating in a monorepo environment containing multiple interconnected services.

• Hands-on experience with MCP or in building tool-use agentic workflows.

• Knowledge of Langfuse or other LLM observability/evaluation platforms.

• Experience in managing AI workloads at scale.

• Background in evaluating various foundation models and providers.

• Proven experience in building AI copilots, assistants, or conversational products.

• Familiar with semantic search and retrieval architectures.

• Experience with AI gateways such as Portkey or similar platforms.

• Proficient with NestJS modules, providers, guards, interceptors, and dependency injection patterns.

• Background in customer support or player support platforms.

• Experience delivering projects under low-latency constraints, such as chatbot response-time budgets and streaming requirements.

• Previous experience in gaming or high-volume consumer products.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Flexible working hours and remote work opportunities.

• Comprehensive health and wellness benefits.

• Opportunities for professional development and career advancement.

• Collaborative and inclusive work environment.