Senior Agentic Backend Engineer

About the Company

Growtrics is an AI EdTech company building the infrastructure layer for personalized learning at scale. Our core products span AI-generated educational video, adaptive learning paths, automatic grading and feedback, and agentic workflows that coordinate across LLMs, content systems, and human reviewers.

About the Role

This is not a backend engineering role that happens to use AI tools.

This is a role for someone who thinks in LLM architectures first — someone who understands how language models fail, how to build reliable systems around non-deterministic inference, how to evaluate and audit AI output at scale, and how to wire all of that into production backends that actually hold up.

We are looking for someone who can take a vague product or operations problem, scope it themselves, choose the right architecture, build it end to end, and own the outcome. No spec handed to you. No architect above you. You will be the one figuring it out. If your instinct when starting a new project is to reach for an LLM and reason about the system from there — if you think in agents, pipelines, evaluation loops, and structured outputs before you think in endpoints and tables — this role is for you

Responsibilities

• Content generation pipelines — multi-agent systems that produce questions, explanations, and learning sequences at scale, with structured output contracts and LLM as-judge quality gates
• Cost and reliability architecture — designing generation systems where cost-per output is a first-class engineering metric, and reliability is achieved through smart fallback and evaluation, not just redundancy
• AI-generated video — multi-stage agentic pipelines that plan, script, render, audit, and revise short-form educational video using LLMs and code generation
• Learning path intelligence — pipelines that reason over learner behavior and content metadata to make real-time personalization decisions

Qualifications

End-to-End Ownership

You take problems from first principles to production—asking the right questions early, identifying real constraints, and delivering systems that work, not just demo. You don't need a PM to keep you moving or an architect to validate your decisions.

AI-Native Thinking

You design systems where LLMs are a core structural component, not a sprinkle on top. You can choose the right model for the cost-latency-quality tradeoff, write prompts that behave reliably at scale, enforce structured outputs with schemas and validation, and build eval/audit loops that catch failures before users do. You know when an agent should hand off, retry, ask a human, or fail closed—and you treat LLM nondeterminism as a first-class engineering constraint.

Strong Backend Foundations

Deep, practical experience with async job execution, durable queues, state machines, idempotency, retries, and observability. You know why Background Tasks isn't a job queue, when to reach for Pub/Sub vs. Cloud Tasks vs. Redis, and how to design for graceful recovery from partial failure.

Independent Operation

You work best when trusted with a problem. You raise blockers early, communicate tradeoffs clearly, and don't disappear into long implementation cycles without surfacing course-correction points.

Required Skills

• 4–10 years backend engineering, including 2+ years building agentic/LLM systems in production
• Deep Python proficiency—async, type-safe, well-tested
• Hands-on multi-agent pipelines: tool use, structured output, eval loops, retry/repair, human-in-the-loop
• Experience across multiple LLM providers (OpenAI, Anthropic, Gemini) and their distinct failure modes, pricing, and limits
• Agent orchestration frameworks (LangGraph, LangChain, CrewAI) or the judgment to know when not to use them
• Strong FastAPI experience and cloud-native async infrastructure (Cloud Tasks, Pub/Sub, Cloud Run, or equivalent)
• Ability to scope and architect systems independently with explicit tradeoffs

Strong Advantage

• Agentic coding harnesses (Claude Code, Codex, Cursor) as a daily driver for real system design
• LLM evaluation frameworks: judge panels, rubric scoring, output auditing
• Firestore/Firebase/GCP, vector databases + RAG (Qdrant, Weaviate, Milvus)
• Code-gen pipelines (AST validation, sandboxed execution), cost observability, and AI-system DevOps/CI/CD

What We Are Not Primarily Looking For

We are not looking for engineers who are strong at backend fundamentals alone and are now learning AI. We have junior engineers who are still building that foundation. For this role, AI-native reasoning is the baseline. Backend depth is the complement.

Preferred Skills

• Systems thinker — you see the problem behind the problem and design for failure modes, not just the happy path
• Clear communicator — you can explain a complex architecture in two paragraphs and flag a risk in one sentence
• High autonomy, low drama — you run hard at problems independently, surface blockers early, and keep the team informed without needing to be chased
• Strong written English — most of our async communication is in writing
• Quick verbal communication — you can explain a decision, a tradeoff, or a status update clearly and concisely on a call without needing to over-prepare
• Decisive under uncertainty — you make reasonable architecture choices with incomplete information and commit to them, rather than waiting for perfect clarity

Pay range and compensation package

• Up to 150,000,000 VND per month, depending on experience and performance. Compensation within this range is calibrated on:
• Demonstrated ability to scope and ship end-to-end systems independently
• Depth and reliability of AI/LLM architecture work
• Production track record — not just shipping, but operating and iterating
• Performance during the hiring process itself (the async challenge and live interview are evaluative, not just screening

Why Join Growtrics

• Competitive compensation package, including 100% salary during probation
• 13th-month salary & performance bonuses
• Full social insurance on gross salary
• Premium health care
• 14 annual leave days + 6 sick days
• Flexible working hours
• MacBook provided
• No strict dress code (comfortable but professional)
• Full compliance with the Vietnam Labor Code
• Employee well-being perks (gym membership, social events, Thursday drinks, fruit served twice a week)
• Opportunity to work with global stakeholders
• Dynamic, international, and creative work environment
• Pantry stocked with snacks & beverages
• Recognition based on skills and performance
• Strong learning & career development opportunities