About the role
structured by ORIWe're building LLM-powered products, and we need a junior engineer who can take an idea from a notebook to a production API. You'll work across the full applied-AI stack: retrieval pipelines, prompt design, open-source model serving, evaluation, and the backend services and cloud infrastructure that hold it all…
What you will do
- Work across the full applied-AI stack: retrieval pipelines, prompt design, open-source model serving, evaluation, and the backend services and cloud infrastructure that hold it all together.
- Pair with senior engineers, ship small pieces early, and grow into owning features end to end.
What they are looking for
- Strong Python fundamentals ? clean, readable, tested code
- Hands-on experience (projects, internships, or work) with LLM APIs or open-source models
- Understanding of how RAG works and where it breaks ? chunking strategy, retrieval quality, context limits
- Experience building REST APIs, ideally with FastAPI
- Working knowledge of Docker ? building images, running containers, docker-compose
- SQL proficiency; comfortable with MySQL or a similar relational database
- Basic familiarity with AWS core services
- Git and a collaborative development workflow (branches, pull requests, reviews)
- Fast API and Relational DB needed.
Nice to have
- Vector databases: pgvector, Qdrant, Chroma, FAISS, or similar
- Frameworks: LangChain, LlamaIndex, or a from-scratch equivalent ? and knowing when not to use them
- Eval tooling: Ragas, DeepEval, promptfoo, or custom harnesses
- LLM observability: Langfuse, LangSmith, or OpenTelemetry-based tracing
- Fine-tuning basics: LoRA/QLoRA, PEFT, dataset preparation
- CI/CD (GitHub Actions), infrastructure-as-code, or Kubernetes exposure
- Contributions to open-source AI projects or a public portfolio
Full posting text
We're building LLM-powered products, and we need a junior engineer who can take an idea from a notebook to a production API. You'll work across the full applied-AI stack: retrieval pipelines, prompt design, open-source model serving, evaluation, and the backend services and cloud infrastructure that hold it all together. You'll pair with senior engineers, ship small pieces early, and grow into owning features end to end.
This is a hands-on role. We care more about what you've built than what you've memorised.
Must have
Strong Python fundamentals ? clean, readable, tested code
Hands-on experience (projects, internships, or work) with LLM APIs or open-source models
Understanding of how RAG works and where it breaks ? chunking strategy, retrieval quality, context limits
Experience building REST APIs, ideally with FastAPI
Working knowledge of Docker ? building images, running containers, docker-compose
SQL proficiency; comfortable with MySQL or a similar relational database
Basic familiarity with AWS core services
Git and a collaborative development workflow (branches, pull requests, reviews)
Fast API and Relational DB needed.
Nice to have
Vector databases: pgvector, Qdrant, Chroma, FAISS, or similar
Frameworks: LangChain, LlamaIndex, or a from-scratch equivalent ? and knowing when not to use them
Eval tooling: Ragas, DeepEval, promptfoo, or custom harnesses
LLM observability: Langfuse, LangSmith, or OpenTelemetry-based tracing
Fine-tuning basics: LoRA/QLoRA, PEFT, dataset preparation
CI/CD (GitHub Actions), infrastructure-as-code, or Kubernetes exposure
Contributions to open-source AI projects or a public portfolio
Seniority level: Entry level
Employment type: Full-time
Industries: Technology, Information and Media