Senior AI Systems Engineer – Data & Platform Architecture

About the role

Plutus21 is seeking a Senior AI Systems Engineer to design and own the data and AI platform that supports internal operations, client integrations, and quantitative‑research tooling. You will lead the architecture of scalable, governed data systems and build retrieval‑augmented generation (RAG) and agentic AI layers on top of them.

Key responsibilities

• Architect and maintain the firm’s data platform, including warehousing, schema and data modeling, ETL/ELT pipelines, and data governance for internal and client workloads.
• Design and implement production RAG and agentic AI systems—vector storage, embeddings, retrieval pipelines, and multi‑agent workflows—for large‑scale document processing.
• Build high‑concurrency backend services and orchestration for high‑volume data processing.
• Operate cloud infrastructure (AWS and/or GCP) using Terraform/IaC, CI/CD, containerization, monitoring, and cost‑optimization.
• Replace manual, error‑prone workflows with automated, well‑documented systems that include appropriate controls, error handling, and human‑in‑the‑loop review.
• Implement authentication, authorization, data access controls, and security best practices for sensitive financial data.
• Set technical direction, conduct code and design reviews, and mentor engineering team members.
• Partner with stakeholders and leadership to scope problems and deliver solutions independently.

Required profile

• 4+ years of software or data engineering experience with ownership of data architecture, warehousing, schema modeling, ETL/ELT pipelines, and governance.
• Proven experience building production RAG or retrieval‑augmented AI systems using vector databases, embeddings, LangChain/LangGraph, and LLM APIs (OpenAI, Anthropic, etc.).
• Strong backend engineering skills in Python and experience with high‑volume, high‑concurrency system design.
• Multi‑cloud experience (AWS and/or GCP) with Terraform/IaC, CI/CD pipelines, and container orchestration (Docker/Kubernetes).
• Fluency with relational and non‑relational databases and data‑pipeline design.
• Sound judgment on automation versus human review, high attention to detail, and integrity with confidential data.

Required skills

• Python
• FastAPI or Django
• AWS
• GCP
• Terraform / IaC
• Docker
• Kubernetes
• BigQuery
• dbt
• Airflow
• Vector databases
• Embeddings
• LangChain / LangGraph
• OpenAI API
• Anthropic API
• LLM APIs