Ai Engineer - Remote

Model service topology, dependencies, deployments, SLOs, runbooks, incidents, and evidence as a knowledge graph.

Build and optimize pgvector indexes, and continuously improve retrieval quality using quantitative metrics rather than subjective evaluation.

Develop ETL pipelines to transform observability data (metrics, logs, and traces) into knowledge graph nodes and relationships.

Generate training and evaluation datasets for LLM agents, including tool-call trajectories, hard-negative samples, and labeled taxonomies.

Design mechanisms to prevent data leakage across training, validation, and test datasets for different incident scenarios.

3+ years of hands-on experience in Data Engineering or Machine Learning Engineering within production environments, with strong proficiency in Python and SQL.

Solid experience in graph data modeling and hands-on experience with at least one graph database, such as Neo4j, PostgreSQL with Apache AGE, or Memgraph.

Proven experience building and operating production-grade RAG (Retrieval-Augmented Generation) systems, with the ability to measure and optimize retrieval quality using quantitative metrics.

Hands-on experience with vector search technologies (e.g., pgvector or equivalent) and a strong understanding of the trade-offs between different indexing strategies.

Experience developing and operating ETL pipelines using workflow orchestration tools such as Airflow, Dagster, Flink, or similar platforms.

Fluent English communication skills.

Salary:

+ 3-5yoe: Up to 31M

+ 5yoe+: Up to 37M

Receive 100% salary from the onboarding date.

Participate in company activities: Teambuilding, travel, vacation and other activities.

Work with large and advanced systems, have the opportunity to develop comprehensive technology skills with complex problems, requiring high accuracy.