Fullstack Web Engineer
Everforth Apex
Bellevue, United States of America
yesterday
Role details
Contract type
Temporary contract Employment type
Full-time (> 32 hours) Working hours
Regular working hours Languages
EnglishJob location
Remote
Bellevue, United States of America
Tech stack
JavaScript
API
Artificial Intelligence
Amazon Web Services (AWS)
Databases
Elasticsearch
PostgreSQL
Redis
E2e Testing
Search Technologies
TypeScript
Network Routers
Chatbots
React
Large Language Models
Prompt Engineering
State Machines
Model Validation
Caching
Backend
WebPack
Kubernetes
Playwright
Sentry
Hashicorp
Kafka
Front End Software Development
React
NestJS
REST
Docker
Service Stack
Job description
This role involves building and evolving the AI systems that power player support. The position entails ownership of the technology stack, from LLM orchestration and agentic workflows using NestJS, XState, and OpenAI, to developing React applications and the administrative tools that manage them., * Design and extend production-grade LLM applications and agentic workflows using NestJS, XState v5, and the OpenAI SDK.
- Build and maintain the conversation-machine substrate, including guard/action registries, flow validation, and design-time tooling.
- Develop the AI systems for the player-facing support chatbot and the AI copilot used by customer support agents.
- Integrate with Model Context Protocol (MCP) servers for tool-use and agentic behaviors.
- Evaluate, benchmark, and tune models from providers such as OpenAI, Gemini, and Anthropic, owning model selection decisions.
- Troubleshoot production LLM issues, including hallucinations, retrieval failures, and latency bottlenecks.
- Build resilience mechanisms like retries, fallback routing, caching, and rate limiting.
- Instrument and tune model quality using tools like Langfuse for tracing and evaluation.
- Manage asynchronous workloads via BullMQ and caching with Redis, with PostgreSQL for persistence.
- Build player-facing and support-agent-facing experiences in React 18.
- Develop and maintain the administrative UI for flow building, intent management, and AI configuration.
- Write comprehensive unit, integration, contract, and end-to-end tests.
- Participate in an on-call rotation to respond to production incidents., You will join a small, senior team within the Player Support engineering organization. The team is responsible for the AI-powered support experience for players, an AI copilot for customer support agents, and the administrative UI for managing AI behaviors. The work includes both greenfield projects and mature systems.
Requirements
- Proven experience building and operating production LLM-powered systems such as chatbots, AI assistants, or RAG systems.
- Strong TypeScript/Node.js engineering proficiency and TypeScript strict-mode fluency.
- Production AI experience, including prompt engineering, RAG pipelines, agent design, and model evaluation.
- Full-stack depth with the ability to work across APIs, UIs, databases, and infrastructure.
- Ability to troubleshoot complex AI systems across prompts, retrieval pipelines, and application code.
- Experience with state machine concepts for modeling asynchronous workflows; XState experience is a strong signal.
- Solid understanding of REST API design, asynchronous patterns, and caching strategies.
- A strong testing culture with experience in unit, integration, and contract testing.
- Experience working in a monorepo with multiple interconnected services.
Technical Skills:
- LLM / AI: OpenAI SDK, Anthropic SDK, Gemini APIs, LangChain, Langfuse, XState v5, MCP SDK.
- Backend: TypeScript, NestJS 11 (Fastify), PostgreSQL, Kysely, Redis, BullMQ, Elasticsearch.
- Frontend: React 18, React Router, Redux/Alt, Webpack, Socket.io.
- Infrastructure / Ops: Docker, HashiCorp Vault, AWS, Kafka, Helm/Kubernetes, OpenTelemetry, Sentry.
- Testing: Jest, Testcontainers, Pact (contract), Playwright (E2E).
Preferred Qualifications
- Hands-on experience with Model Context Protocol (MCP) or building tool-use agentic workflows.
- Familiarity with Langfuse or other LLM observability platforms.
- Experience operating AI workloads at scale and evaluating multiple foundation models.
- Experience building AI copilots, assistants, or conversational products.
- Experience with semantic search and retrieval architectures.
- Specific experience with NestJS patterns such as modules, providers, and guards.
- Background in customer support or player support platforms.
About the company
Everforth Apex is a world-class IT services company that serves thousands of clients across the globe. When you join Everforth Apex, you become part of a team that values innovation, collaboration, and continuous learning. We offer quality career resources, training, certifications, development opportunities, and a comprehensive benefits package. Our commitment to excellence is reflected in many awards, including ClearlyRateds Best of Staffing in Talent Satisfaction in the United States and Great Place to Work in the United Kingdom and Mexico.
Everforth Apex uses a virtual recruiter as part of the application process. Click for more details. By applying for this job, you agree to receive calls, AI-generated calls, text messages, or emails from Everforth Apex and its affiliates, and contracted partners. Frequency varies for text messages. Message and data rates may apply. Carriers are not liable for delayed or undelivered messages. You can reply STOP to cancel and HELP for help. You can access our privacy policy at