RESPONSIBILITIES
- Support development of AI/LLM features (API calls, embeddings, RAG components).
- Assist in building and debugging backend services using Python/FastAPI.
- Read logs, troubleshoot issues, and write clean, logical code.
- Collaborate using Git (branching, merge requests, conflict resolution).
- Report progress consistently and meet sprint deadline.
REQUIREMENTS
Must-Have
- Python
- Strong foundation in Python (JSON, list/dict, API calls).
- Experience with FastAPI or ability to learn quickly.
- AI / LLM
- Basic understanding of RAG, embeddings, vector search.
- Knowledge of core AI/ML concepts (overfitting, precision/recall, train/val/test).
- Understanding of LLM fundamentals (tokens, tokenization, context window).
- Completed at least 1–2 AI/ML projects.
- DevOps Basics
- Able to run Docker containers, read logs, restart services.
- Basic Linux knowledge.
- Git/GitLab
- Create Merge Requests, follow team branching workflow.
Nice to Have
- Experience with FastAPI, Qdrant/Neo4j, RAG pipelines.
- Familiarity with AI Agent frameworks (REACT, LangChain, AutoGen, MCP).
- Knowledge of Rust, TypeScript, or graph databases.
HOW TO APPLY
Step 1: Submit Your CV
Apply directly through the Innotech Vietnam Corporation website by uploading your updated CV to the careers section.
Step 2: Phone Screening
If shortlisted, you will receive a call from the HR team for a brief survey and initial screening.
Step 3: Interview
Qualified candidates will be invited to an interview to further assess suitability for the role.
Step 4: Onboarding
Successful applicants will receive an offer and begin the onboarding process to officially join the team.
