Sottava
Scanning 1,182 companies · 30,491 open jobs · last pass 42 min ago

← Sottava, jobs the hour they open

2 mo agofound 3 h ago

Senior AI Engineer

Avenga·Skopje, South-Eastern Europe, MK, Ohrid, Bitola·via teamtailor
What the posting is about

Develop core engine of AI assistant using RAG and LLM orchestration. Design and build REST APIs, work with vector databases and LLM providers. Collaborate in a team using GitHub and write automated tests with pytest. Nice-to-have: experience with LlamaIndex, Milvus, Azure OpenAI, and multilingual NLP.

Read out of the posting
Levelsenior
Experience asked3+ years
EmploymentFull time
LocationSkopje, South-Eastern Europe, MK, Ohrid, Bitola
RemoteNot stated
Visa sponsorshipNot stated
SalaryNot published, and most postings do not
Posted2026-07-23
Found viateamtailor, direct from their system

We saw it 2 months after it went up.

The posting, as the company wrote it
Avenga is an international engineering firm helping businesses operate with AI at the core. With 6,000+ experts worldwide, we combine engineering expertise with AI-native thinking to turn ambitious ideas into real-world impact across industries, technologies, and markets. At the core of the role You'll be working on the core engine of a production AI assistant, developing Agentic AI solutions using RAG and LLM orchestration to enable the assistant to move beyond answering questions and safely execute real customer requests. Core skills you’ll bring 3+ years building production Python services (async, API design) Experience designing and building REST APIs (and consuming them); comfortable with request/response modelling, auth, and versioning Hands-on experience building RAG / retrieval-augmented generation systems: not just calling an LLM API, but chunking, retrieval, and grounding answers in sources Experience with any vector database (e.g. Milvus, Pinecone, Weaviate, Qdrant, pgvector) and an understanding of embeddings and similarity search Worked with an LLM provider (OpenAI / Azure OpenAI / Anthropic / open models) in production A habit of evaluating output quality, you can explain how you measured whether a RAG system was good Writes automated tests as a matter of habit unit and integration testing with pytest (mocking, fixtures) Comfortable with GitHub in a team workflow, feature branches, pull requests, and code review Nice-to-have: LlamaIndex (or LangChain) framework experience Milvus specifically Azure OpenAI deployments LLM observability / tracing (Langfuse, LangSmith, OpenInference) FastAPI, Pydantic WebSocket / streaming APIs for real-time chat responses API tooling and testing: Bruno / Postman, OpenAPI/Swagger; API gateways Async & parallel testing and mocking AWS Modern Python tooling: uv, ruff, ty/mypy, pre-commit CI/CD with GitHub Actions, and trunk-based development with Conventional Commits AWS (ECS/Fargate, Secrets Manager), Terraform, Docker Multilingual NLP (Dutch/English) People are at the core of Avenga. We provide equal opportunities regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to a respectful environment where everyone can be themselves, share their ideas, and feel that they belong.

Copied from Avenga’s own board, not rewritten. Original ↗

Also open at Avenga

Why this page exists

We read companies’ own hiring systems every hour, 1,182 of them, and show a job the hour it opens instead of when a job board gets around to indexing it. We saw it 2 months after it went up.

The feed is free. No card, no trial to expire.