AI Engineer
Core
Design, prototype, and deploy retrieval-augmented generation (RAG) systems and hybrid retrieval pipelines for AI-driven applications.
Role type
Senior IC AI Engineer (Retrieval & RAG)
Builds
Scalable RAG pipelines, vector search systems, knowledge graphs, and hybrid retrieval workflows.
Domain
Generative AI, Information Retrieval, Knowledge Graphs
Deliverable
production ML models
Required skills
Python, RAG system design, vector databases (pgvector, FAISS, Milvus, Weaviate), embedding strategies, LLM frameworks (Hugging Face, LangChain, LlamaIndex), distributed systems, Docker, Kubernetes, cloud platforms (Azure, AWS, GCP)
Preferred skills
Knowledge graphs, LLM fine-tuning, RLHF, multimodal AI, React/Next.js
Technologies
Milvus, pgvector, FAISS, Weaviate, Neo4j, RDF, TensorFlow, PyTorch, OpenAI, Cohere, Sentence Transformers, Hugging Face Transformers, LangChain, LlamaIndex, Docker, Kubernetes, Azure, AWS, GCP
Responsibilities
Architect scalable RAG pipelines combining vector search and hybrid retrieval; Build and integrate vector search systems for high-recall retrieval; Design hybrid retrieval systems blending semantic, symbolic, and graph-based methods; Architect knowledge graphs and integrate them into retrieval workflows; Optimize data pipelines and embeddings for AI retrieval; Implement hybrid search and metadata filtering; Evaluate and monitor system performance using IR metrics and LLM-specific evaluations; Compare and fine-tune LLMs to meet latency and cost targets.
Seniority
Mid-to-Senior, hands-on IC