Applied AI Engineer
Core
Evaluate and integrate the latest AI models and retrieval techniques into a production-grade open-source AI search platform (Vespa) to enable semantic/hybrid search, RAG, and recommendation capabilities for enterprise users.
Role type
Applied AI Engineer (IC)
Builds
Integrations between Vespa and AI frameworks (ONNX, Hugging Face, LLM APIs), reference applications, benchmarks, and demonstrations.
Domain
AI/ML, Search Engines, Vector Databases, Enterprise Software
Deliverable
production ML models
Required skills
Python, Java, Embedding models, Transformer models, LLMs, Retrieval techniques, ML inference in production, Software engineering principles
Preferred skills
RAG, Hybrid search, Recommendation systems, ONNX, Hugging Face, LangChain/LlamaIndex, Open-source contributions
Technologies
Vespa, Python, Java, ONNX, Hugging Face, PyTorch, GitHub, Grafana, Slack
Responsibilities
Track developments in embedding models, rerankers, LLMs, and retrieval techniques; Design and build integrations between Vespa and current models/frameworks; Build and maintain reference applications, benchmarks, and demonstrations; Propose and prototype improvements to Vespa for AI workloads; Work with users/customers to understand AI use cases; Contribute technical content (sample apps, documentation).
Seniority
Mid-Senior, hands-on IC