Senior AI Engineer (Search / Retrieval)
Core
Build the retrieval layer that powers enterprise AI agents by stitching together data from heterogeneous sources (Salesforce, Zendesk, Jira, etc.) into ranked, permission-aware responses.
Role type
Senior IC machine-learning engineer (search & retrieval)
Builds
Unified retrieval layer, hybrid retrieval pipelines, ingestion/freshness pipelines, and production-grade observable systems for enterprise AI agents.
Domain
Enterprise SaaS / AI Infrastructure / Information Retrieval
Deliverable
production ML models | product features
Required skills
Information Retrieval fundamentals (BM25, TF-IDF, learning-to-rank), vector search and embeddings, RAG pipeline design, SaaS API integrations, SQL and NoSQL, distributed systems, cloud platforms (AWS/GCP/Azure), containerization, CI/CD.
Preferred skills
Knowledge graphs, entity resolution, embedding model tuning, agentic AI patterns (MCP, tool use), streaming ingestion (Kafka, Flink), observability.
Technologies
OpenSearch, Elasticsearch, Solr, Vespa, FAISS, pgvector, Pinecone, Weaviate, Qdrant, Milvus, LangChain, LlamaIndex, Haystack, Python, Go, Java, Kafka, Flink, Spark.
Responsibilities
Build a unified retrieval layer across enterprise systems; Design hybrid retrieval pipelines combining lexical, dense vector, and structured retrieval; Engineer ingestion and freshness pipelines; Own permission-aware retrieval (ACL preservation); Build query understanding for agents; Design chunking and embedding strategies; Build evaluation and experimentation harnesses; Ship production-grade, observable systems; Mentor teammates.
Seniority
Senior, hands-on IC
