Design and manage end-to-end data ecosystems that ingest, clean, and organize unstructured data from fragmented sources into high-performance Vector Databases

.

Build the "Context Engineering" pipelines that feed our AI agents, ensuring they have the right data at the right millisecond to reduce hallucinations and maximize reasoning.

Design and monitor Agentic Flows

and perform deep Trace Analysis

to debug how data processing impacts model performance.

Leverage Cursor, and automated agents to accelerate code generation, optimize SQL/Python, and maintain a "Fast Delivery" culture.

Act as a Full-Stack contributor—building the APIs that expose data to models while ensuring the underlying infrastructure is robust, scalable, and secure.

Proven experience in building end-to-end applications (Node.js, Python, or Go) and managing cloud infrastructure (MUST).

Expert-level knowledge of ETL/ELT, data lake architectures (Delta Lake, Iceberg), and real-time processing (Kafka/Flink).

Familiarity with Vector DBs (Pinecone, Weaviate, Milvus), orchestration frameworks (LangChain, LlamaIndex), and trace analysis tools.

Ability to perform complex scale-level analytics to prove model ROI.

You understand the fundamentals of LLMs, embedding models, and how data quality directly influences RAG

(Retrieval-Augmented Generation).

You have a "can-do" attitude and a bias toward action. You prefer shipping a working prototype today over a perfect slide deck tomorrow.

You can jump from a Cyber-security data audit to optimizing a real-time streaming pipeline without breaking stride.

You view data as an asset to be refined, not just a chore to be managed.