AI Platform Engineer (Remote)

We are looking for talented AI developers to join our dynamic team in Vietnam. If you have experience with production-grade AI and have excellent English communication, we want to hear from you.

Responsibilities:

• Develop and maintain agentic LLM workflows (tool/function calling, multi-step planning, RAG graphs) using established patterns and frameworks.
• Build production services/APIs (prompt/version management, caching/fallbacks, eval pipelines) with strong observability for latency, quality, and cost.
• Improve retrieval quality and functionality with agentic tools: embeddings strategy, chunking/metadata, hybrid dense–sparse search, reranking; measure via offline/online evaluations and A/B tests.
• Operate in cloud environments with containerized services, CI/CD, infrastructure-as-code, distributed tracing/telemetry, and cost/performance guardrails.
• Contribute to safety, security, and compliance (guardrails, content filters, PII handling, tenancy, audit logging).
• Collaborate with product and domain experts to translate simulation/graphics workflows into trustworthy AI features with measurable impact.
• Senior scope: help guide system architecture and technical direction; mentor teammates; elevate standards for reliability, security, and efficiency in performance.

Qualifications:

• 2–5+ years in backend/platform engineering (Senior typically 5+), with examples of production releases.
• Python proficiency for production systems (testing, packaging, typing). Experience in a compiled language for systems/application work is a plus.
• Hands-on experience with LLM frameworks and agentic tooling (multi-tool workflows, function execution, orchestration graphs).
• Practical RAG: embeddings, vector stores, metadata/indexing strategies, hybrid search, rerankers.
• Cloud fluency with containerized development and deployment; CI/CD; familiarity with serverless or Kubernetes.
• API development (REST/gRPC), auth/secrets management, and performance/cost awareness.
• Creative, adaptable problem-solver who stays current with a fast-moving AI ecosystem.

Preferred experiences:

• Full-stack React meta-frameworks supporting SSR/ISR and edge/serverless runtimes (or equivalent).
• Relational databases (SQL) with vector indexing/extensions, plus schema design, migrations, and performance tuning.
• Desktop runtimes that package web apps into cross-platform desktop applications.
• Protocol-oriented agent tool servers for LLM integrations and secure tool execution.
• Observability & ops (distributed tracing, application metrics, LLM telemetry); advanced evals/guardrails/testing; data systems (caches, queues/streams).
• Domain familiarity with numerical simulations, computational geometry, or 2D/3D visualization.