About the Opportunity On behalf of our client—a fast-growing technology company pioneering conversational AI and intelligent automation—we are seeking a Full-Stack AI Engineer to build next-generation customer experiences. This role places you at the intersection of large language models (LLMs), real-time voice interactions, and modern web technologies. You will design, orchestrate, and deploy production-grade AI agents, leveraging the Model Context Protocol (MCP) and low-latency voice pipelines to create highly capable, autonomous user experiences at scale.

Location: 100% Remote from Vietnam.

Employment Type: Full-Time.

Key Responsibilities

• Production Agent Orchestration: Architect and deploy robust single- and multi-agent systems (OpenAI, Anthropic) with complex routing, tool calling, state management, and recovery logic, primarily utilizing the Vercel AI SDK.
• Real-Time Voice Infrastructure: Build and optimize low-latency voice pipelines featuring streaming STT/TTS, sub-second turn-taking, clean barge-in handling, and emotion-aware responses over WebRTC transport layers (managing audio rooms, agent workers, and session lifecycles).
• MCP & System Integration: Develop Model Context Protocol (MCP) servers and clients to securely connect agents to database contexts, alongside implementing agentic browser automation to execute real-world tasks.
• Full-Stack Feature Delivery: Ship end-to-end features utilizing Node.js (TypeScript) and React/Svelte, streaming agent states via AG-UI, and developing framework-agnostic, embeddable web widgets.
• Performance & Security Optimization: Tune AI systems for latency, cost, and reliability through intelligent caching, fallback strategies, and streaming. Implement comprehensive tracing (Langfuse, OpenTelemetry), run online A/B tests, and enforce rigorous security measures (prompt-injection defense, PII masking).

Requirements

• Engineering Foundation: 5+ years of production engineering experience, heavily focused on Node.js and advanced TypeScript.
• Production AI Agents: Proven hands-on experience building and deploying complex LLM applications (tool calling, structured outputs, multi-step orchestration, context management), with a strong preference for Vercel AI SDK expertise.
• Real-Time Voice/Streaming: Production experience engineering real-time audio pipelines (STT/TTS, turn detection, latency tuning) and managing WebRTC infrastructure.
• Agent Protocols: Deep familiarity with the Model Context Protocol (MCP), AG-UI, and agent-driven browser automation frameworks.
• Frontend Mastery: Strong proficiency in React or Svelte, with a track record of building embeddable components for multi-tenant and third-party environments.
• AI Security & Evaluation: Strong grasp of prompt engineering, non-deterministic debugging, agent evaluation, and security-first development (input validation, secrets management, least-privilege principles).

Preferred Qualifications

• Bachelor’s degree in Computer Science, Engineering, or a related technical field.
• Deployment and operational experience on AWS and Vercel serverless/edge runtimes.
• Familiarity with RAG architectures, vector databases, and complex retrieval pipelines.
• Experience with model routing, fine-tuning, and evaluating model cost-benefit trade-offs.
• Background in conversational commerce, personalization, or consumer web conversion rate optimization (CRO).
• Knowledge of WCAG AA accessibility standards tailored for voice and conversational interfaces.

Benefits

• Competitive base salary paid in USD.
• Comprehensive social insurance coverage in accordance with Vietnamese labor regulations.
• 20 days of annual leave plus 10 public holidays per year.
• Company-provided high-performance laptop.
• 100% remote working environment.
• Sponsored continuous learning (training, workshops, and industry conferences).
• Clear career growth opportunities with dedicated support from local and international technical leadership.