As a Backend Engineer, you will design and develop the core backend services that enable AI applications at scale. You will build highly available microservices, APIs, agent runtime services, and platform capabilities supporting millions of requests, real-time AI interactions, and secure enterprise integrations. You will work closely with AI Engineers, Data Engineers, Product Managers, and Platform Engineers to deliver production-grade backend systems for both cloud and edge AI.
This role is ideal for engineers who enjoy building scalable distributed systems, solving complex backend challenges, and creating reusable platform capabilities rather than developing isolated business applications.
Backend Platform Development
- Design, develop, and maintain scalable backend services using
microservice architecture.
- Build core platform services including API Gateway, Authentication,
Authorization, User Management, Tenant Management, and Configuration Services.
- Develop RESTful APIs, gRPC services, WebSocket, and Server-Sent Events
(SSE) for real-time communication.
- Design backend services with high availability, scalability, and fault
tolerance.
- Develop backend services supporting AI Agents, RAG, Prompt Management,
Conversation Management, and Tool Calling.
- Build Model Gateway to integrate multiple LLM providers (OpenAI, Azure
OpenAI, Gemini, Claude, Qwen, DeepSeek, Ollama, vLLM).
- Develop Agent Runtime services for orchestration, context management,
memory, and workflow execution.
- Support streaming AI inference and low-latency AI interactions.
- Design asynchronous architectures using message queues and event-driven
patterns.
- Integrate backend services with enterprise systems through REST APIs,
gRPC, Kafka, MQTT, and webhooks.
- Develop reliable background processing services using Redis, BullMQ, or
equivalent technologies.
- Ensure services are idempotent, resilient, and support retry and
recovery mechanisms.
- Design efficient database schemas for transactional and analytical
workloads.
- Optimize PostgreSQL, Redis, and object storage utilization.
- Collaborate with Data Engineering teams to expose backend APIs for AI
and analytics platforms.
- Implement caching strategies to improve system performance and reduce
infrastructure costs.
- Deploy backend services on Kubernetes using Docker containers.
- Build and maintain CI/CD pipelines with GitLab CI or GitHub Actions.
- Monitor system health, logging, tracing, and alerting using Prometheus,
Grafana, and OpenTelemetry.
- Continuously improve platform reliability, scalability, and operational
efficiency.
- Implement secure authentication and authorization mechanisms (OAuth2,
JWT, API Key).
- Ensure compliance with enterprise security standards and secure coding
practices.
- Build audit logging, API rate limiting, secret management, and access
control mechanisms.
- Collaborate with security teams to maintain secure backend services.
Requirements
Bachelor's
degree or higher in Computer Science, Software Engineering, Information
Technology, or related disciplines.
Minimum 3 years of professional backend development experience.
Experience building production-grade backend systems serving enterprise
applications.
Experience working in Agile software development environments.
Programming Languages
Strong proficiency in TypeScript (Node.js/NestJS).
Experience with Python, Go, or Java is an
advantage.
NestJS
Express.js
REST API
gRPC
WebSocket
Server-Sent Events (SSE)
OpenAPI / Swagger
PostgreSQL
Redis
MongoDB (preferred)
Database schema design and optimization
Microservice Architecture
Event-Driven Architecture
Message Queue
BullMQ
Kafka (preferred)
MQTT (preferred)
Docker
Kubernetes
AWS, Azure, or GCP
GitLab CI / GitHub Actions
Infrastructure monitoring and logging
Experience integrating LLM APIs.
Understanding of RAG architecture.
Prompt Engineering concepts.
AI Agent frameworks (LangGraph, AutoGen, CrewAI) are advantages.
MCP (Model Context Protocol) knowledge is a plus.
Experience building enterprise AI platforms.
Experience with streaming systems and real-time applications.
Experience designing API Gateway or Backend-for-Frontend (BFF).
Experience with OpenTelemetry, Prometheus, and Grafana.
Experience in Automotive, IoT, or Edge Computing.
Ability to read technical documentation and communicate effectively in
English.
Strong system design and problem-solving skills.
Ability to design maintainable, scalable backend architectures.
Excellent communication and collaboration skills.
Strong ownership mindset with attention to reliability and software
quality.
Comfortable working in fast-paced, ambiguous environments.
Passion for building platform products that enable other engineering
teams.
Deliver 5+ production-ready backend services supporting the ViTAI
platform.
Achieve 99.9% service availability across owned services.
Maintain API P95 latency below 200 ms (excluding AI inference
time).
Successfully integrate multiple LLM providers through a unified
Model Gateway.
Build scalable backend services supporting 1M+ API requests/day.
Implement complete observability, including logging, metrics, tracing,
and alerting.
Deliver secure, documented, and reusable APIs adopted by AI, Data, and
Product teams.
Contribute to establishing a standardized backend engineering framework
and best practices across the ViTAI platform.
Benefits
- Competitive salary
- Premium healthcare package, including PVI insurance & annual health check-ups
- 13th-month salary & performance bonuses to reward your contributions
- Enjoy preferential pricing for services within the Vingroup ecosystem including Vinmec, Vinpearl, and Vinschool...
- Opportunity to collaborate with and learn from industry-leading professionals in the automotive domain
Work Location: Technopark Tower, Gia Lam, Hanoi, Viet Nam
With respect to all your personal data shared to VinFast in the application and the entire recruitment process of VinFast, by clicking “Apply”, submitting your resumé/CV and/or participating in VinFast's recruitment process, you agree that you have read VinFast's Personal Data Protection Policy ("Policy") posted at https://vinfastauto.com/vn_vi/dieu-khoan-phap-ly or https://vinfast.vn/privacy-policy/, you agree to the Policy and consent for VinFast to process your personal data in accordance with the Policy and the applicable regulations on personal data protection.
To all recruitment agencies: VinFast does not accept agency resumes. Please do not forward resumes to our careers alias or other VinFast employees. VinFast is not responsible for any fees related to unsolicited resumes.
Skills Required
- Bachelor's degree in Computer Science, Software Engineering, Information Technology, or related discipline
- Minimum 3 years professional backend development experience
- Experience building production-grade backend systems for enterprise applications
- Proficiency in TypeScript (Node.js/NestJS)
- Hands-on with NestJS and Express.js
- Design and develop RESTful APIs, gRPC services, WebSocket, and Server-Sent Events (SSE)
- Experience with PostgreSQL and Redis
- Experience with microservice and event-driven architectures, message queues, and background processing (e.g., BullMQ)
- Containerization and orchestration with Docker and Kubernetes
- CI/CD experience with GitLab CI or GitHub Actions
- Monitoring, logging, and tracing experience (Prometheus, Grafana, OpenTelemetry)
- Implement secure authentication and authorization (OAuth2, JWT, API Key) and enterprise security best practices
- Experience with cloud platforms (AWS, Azure, or GCP)
- Experience with Python, Go, or Java
- MongoDB experience
- Experience with Kafka and/or MQTT
- Experience integrating LLM APIs, RAG architectures, and prompt engineering concepts
- Familiarity with AI agent frameworks (LangGraph, AutoGen, CrewAI) or MCP
- Experience building enterprise AI/real-time streaming platforms and API Gateway/BFF design
What We Do
VinFast is a Vietnamese multinational automotive manufacturer, established in 2017, that designs and manufactures electric vehicles (EVs), e-scooters, and e-buses. It is part of Vingroup, one of Vietnam's largest conglomerates.
.jpeg)
