Senior Python Engineer

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.

• →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.
• →Model Evaluation & Quality Frameworks: Build automated pipelines and tooling to continuously measure, evaluate, and improve LLM output accuracy, consistency, latency, and safety.
• →Developer Tooling & Frameworks: Develop internal libraries, abstractions, and standardized patterns that empower engineering squads to ship AI features quickly and reliably.
• →Production Performance & Cost Optimization: Optimize AI services and inference pipelines for throughput, latency, token economics, caching, and high availability.
• →Architectural Leadership: Partner with the CTO and technical leads to evaluate emerging AI technologies, architect retrieval-augmented generation (RAG) pipelines, and design vector search infrastructure.
• →Engineering Best Practices: Provide technical mentorship, conduct thorough code reviews, and establish rigorous standards for testing, deployment, and operational observability of AI systems.

• 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.
• Systems Design & Problem-Solving: Ability to architect decoupled, scalable services with clear boundaries and maintainable data flows.
• Communication & Team Collaboration: Strong communication skills (both English and Vietnamese) and the ability to articulate architectural decisions clearly across engineering teams.
• Strong understanding of information security and technology governance, with experience ensuring engineering practices follow company security policies and ISO 27001-aligned procedures.

Nice to Have: Experience with FastAPI, RAG, vector databases (Pinecone, Qdrant, Milvus), LLM observability tools (Langfuse, LangSmith), and MLOps/LLMOps infrastructure.