About MISEN
MISEN is building a trusted technology ecosystem where people, teams, and businesses can reach more of their potential through practical software, thoughtful automation, and responsible AI.
Our mission is to create technology that works at the intersection of business and humanity: systems that reduce friction, improve decision-making, and help teams operate with more clarity, speed, and confidence.
About the AI Platform Team
The AI platform team builds applied AI systems for real workflows. We care about model capability, but we care just as much about the engineering discipline required to make AI useful in production: quality checks, evals, observability, cost control, safety boundaries, data pipelines, backend reliability, and interfaces that humans can trust.
This role is for someone who can balance experimentation with production judgment. You should be comfortable exploring new AI tools, but disciplined enough to ask: How do we test this? How do we monitor it? How do we make it safe? How do we know it is actually useful?
Responsibilities
- Build production AI systems using LLM APIs, tool-calling, RAG, structured outputs, and agent workflows.
- Design evaluation loops for quality, factuality, latency, cost, safety, and regression detection.
- Create backend services, APIs, jobs, queues, and data pipelines that support AI-powered product workflows.
- Implement validation, permission checks, audit trails, monitoring, and guardrails for AI behavior.
- Evaluate new AI tools and turn useful ideas into maintainable platform capabilities.
Representative Projects
- Build an evaluation suite that measures factuality, reasoning quality, cost, latency, and safety for AI workflows.
- Design a tool-calling runtime with structured outputs, schema validation, retries, and failure handling.
- Create a RAG pipeline with scoped retrieval, source attribution, permission-aware access, and quality monitoring.
- Build dashboards for AI run observability, token cost, latency, errors, model drift, and approval outcomes.
You May Be a Good Fit If You
- Have 5+ years of backend, platform, AI, or ML engineering experience.
- Have deployed AI, LLM, automation, or data-heavy systems in production.
- Are strong in Python and/or TypeScript backend development, APIs, SQL, async jobs, and system design.
- Care about reliability, safety, observability, and cost as much as model capability.
- Can explain AI system trade-offs to both engineers and non-technical stakeholders.
Strong candidates may also have
- Experience with RAG, embeddings, vector databases, evals, AI agents, structured outputs, or prompt/version management.
- Experience with OpenAI, Anthropic, Gemini, LangChain, LlamaIndex, pgvector, Pinecone, Weaviate, Docker, Kubernetes, or AI observability tools.
- Strong instincts for failure modes: hallucination, prompt injection, permission leakage, runaway cost, latency spikes, and brittle automation.
Candidates need not have
- A formal AI research background.
- Experience with every AI framework or model provider.
- A perfectly linear career path.
Logistics
Minimum education: College diploma, associate degree, vocational training in a relevant field, or equivalent practical experience demonstrated through shipped systems, technical leadership, open-source work, platform ownership, or professional training.
Minimum years of experience: 5+ years of backend, platform, AI, or ML engineering experience. Seniority will be assessed based on production ownership, reliability judgment, system complexity, and communication.
Location-based hybrid policy: Hanoi hybrid is preferred. Remote-flexible arrangements can be considered for exceptional candidates in Vietnam.
Compensation: Annual Salary USD $30,000 - $45,000 gross. This range is base annual gross salary. The compensation package also includes guaranteed 13th-month salary and may include performance-based bonus depending on company and individual results.
Deadline to apply: None. Applications are reviewed on a rolling basis.
We encourage you to apply: You do not need to meet every single qualification. Strong candidates may come from different backgrounds, and we care most about production judgment, ownership, reliability, and learning speed.
What We Offer
- Transparent annual salary range, guaranteed 13th-month salary, and performance-based quarterly or year-end bonus depending on company and individual results.
- Full salary during probation and benefits in accordance with company policy and Vietnam Labor Law.
- 15+ days of paid annual leave, company holidays, and regular team activities or company events.
- Hanoi hybrid is preferred, with remote-flexible arrangements considered for exceptional candidates in Vietnam.
- Practical, high-ownership work where reliability, safety, and product impact matter.
- Deep ownership of AI agent infrastructure, evals, guardrails, model/provider integrations, and production observability.
- Room to shape platform standards for quality measurement, cost control, latency, auditability, and safe rollout.
Apply for this job
Share enough context for us to understand your production AI experience, platform judgment, and shipped work. Specific examples are more useful than a generic cover letter.
After you apply: We review applications on a rolling basis. If there is a strong match, we will contact you for an intro call, followed by a technical/product deep dive and a practical AI systems discussion.