Mô tả công việc
About The Role
We are looking for a Senior Python Engineer to help design, build, and scale the foundational backend systems powering AI across our platform. In this role, you will work closely with our CTO and engineering leads to shape key technical decisions around AI architecture, LLM orchestration, model evaluation, and backend scalability.
You will serve as a core technical anchor, developing reliable frameworks and internal services that enable product squads to safely, efficiently, and rapidly deliver LLM-powered features.
This role is ideal for an engineer who thrives on owning complex system challenges, enjoys optimizing production services, and wants to make a substantial technical impact in applied AI engineering.
Work Location: Hanoi or HCMC
Key Responsibilities
- Architect &
- Scale AI Infrastructure: Design, implement, and maintain robust Python/FastAPI microservices and backend systems that integrate LLMs and generative AI capabilities directly into live workflows.
- Quality Frameworks: Build automated pipelines and tooling to continuously measure, evaluate, and improve LLM output accuracy, consistency, latency, and safety.
- Frameworks: Develop internal libraries, abstractions, and standardized patterns that empower engineering squads to ship AI features quickly and reliably.
- Cost Optimization: Optimize AI services and inference pipelines for throughput, latency, token economics, caching, and high availability.
Requirements
Required Qualifications
- 5 years of professional software engineering experience, with a solid background in backend systems, distributed architectures, and API design.
- Advanced Python expertise: Deep understanding of asynchronous programming (asyncio), performance profiling, clean code architecture, and modern backend development.
- Production AI/LLM Integration: Proven hands-on experience integrating LLM APIs (OpenAI, Anthropic, open-source models) or generative AI capabilities into live production environments.
- System Evaluation &
- Monitoring: Practical experience measuring, evaluating, and improving AI model output quality, latency, and reliability in real-world applications.
- Problem-Solving: Ability to architect decoupled, scalable services with clear boundaries and maintainable data flows.
- Team Collaboration: Strong communication skills (both English and Vietnamese) and the ability to articulate architectural decisions clearly across engineering teams.
Nice to Have
- Hands-on experience with modern Python web frameworks (especially FastAPI).
- Experience with Retrieval-Augmented Generation (RAG), vector databases (e.g., Pinecone, Qdrant, Milvus, pgvector), and embedding pipelines.
- Experience with model fine-tuning, prompt evaluation frameworks, or LLM observability tools (e.g., Langfuse, LangSmith, TruLens).
- Background in building internal developer platforms, tooling, or MLOps/LLMOps infrastructure.
- Experience building scalable B2B SaaS or cloud-native applications.
- Opportunities to work on challenging international software engineering projects.
- Ownership of meaningful technical deliverables and complex engineering challenges.
- A collaborative environment that values engineering excellence, accountability, and knowledge sharing.
- Opportunities to mentor other engineers and contribute to technical best practices.
- Continuous learning and professional development opportunities.
- Long-term career growth within a technology-focused organization.
By submitting your application, you acknowledge that you have read and understood this notice and that the information provided is accurate and complete.
Bạn quan tâm đến vị trí này?