AI Systems Engineer

Plutus21; Sindh; On-site; PKR 3,000,000 - 4,200,000; Full time

Job summary

Plutus21 is seeking a Senior AI Systems Engineer to architect the data and AI platform that powers our internal operations, client integrations, and quantitative-research tooling. You will own the design of scalable, well-governed data systems that ingest and process high volumes of financial and operational documents, and build the retrieval, agentic, and automation layers on top of them.

This is an architecture-owning role that partners with engineering, operations, and the partner group.

Qualifications

• 4+ years of software/data engineering with ownership of data architecture (warehousing, modeling, ETL/ELT, governance).
• Experience designing production RAG/retrieval/agentic AI systems: vector databases, embeddings, LangChain/LangGraph, LLM APIs.
• Strong backend engineering in Python (FastAPI/Django) and high-volume, high-concurrency system design.

Responsibilities

• Architect and own the firm's data platform: warehousing, schema/data modeling, ETL/ELT pipelines, and data governance across internal and client workloads.
• Design and build production RAG and agentic AI systems for document processing, extraction, classification, and validation against source records at scale.
• Build scalable, high-concurrency backend services and orchestration for high-volume data processing.
• Design and operate infrastructure across cloud (AWS and/or GCP) with Terraform/IaC, CI/CD, containerization, monitoring, and cost optimization.
• Identify and replace manual, high-volume workflows with reliable automated systems with proper controls 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 engineers.
• Partner directly with stakeholders and leadership to scope problems and execute independently.

Skills

data architecture

data warehousing

ETL/ELT pipelines

data governance

RAG / retrieval / agentic AI

production-grade Python

multi-cloud (AWS/GCP)

Terraform/IaC

CI/CD

Docker/Kubernetes

LangChain / LangGraph

LLM APIs (OpenAI/Anthropic)

FastAPI/Django

SQL/NoSQL databases

Education

MS in Machine Learning

MS in Computer Science

Tools

BigQuery

dbt

Airflow

LangChain

LangGraph

OpenAI API

Anthropic API

Terraform

AWS

GCP

Docker

Kubernetes

Job description

Job Summary

Plutus21 is hiring a Senior AI Systems Engineer to architect the data and AI platform that powers our internal operations, client integrations, and quantitative-research tooling. You will own the design of scalable, well-governed data systems that ingest and process high volumes of financial and operational documents, and build the retrieval, agentic, and automation layers on top of them. This is an architecture-owning role that partners with engineering, operations, and the partner group.

Key Responsibilties:

• Architect and own the firm's data platform: warehousing, schema and data modeling, ETL/ELT pipelines, and data governance across internal and client workloads.
• Design and build production RAG and agentic AI systems — vector storage, embeddings, retrieval pipelines, and multi-agent workflows — for document processing, extraction, classification, and validation against source records at scale.
• Build scalable, high-concurrency backend services and orchestration for high-volume data processing.
• Design and operate infrastructure across cloud (AWS and/or GCP) with Terraform/IaC, CI/CD, containerization, monitoring, and cost optimization.
• Identify and replace manual, high-volume, error-prone workflows with reliable, well-documented automated systems, with 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 engineers.
• Partner directly with stakeholders and the leadership group to scope problems and execute independently.

Required Qualifications

• 4+ years of software/data engineering, with demonstrated ownership of data architecture — data warehousing, schema/data modeling, ETL/ELT pipelines, and data governance. (BigQuery, dbt, Airflow, or equivalent.)
• Proven experience designing production RAG / retrieval / agentic AI systems: vector databases, embeddings, LangChain/LangGraph or equivalent, and LLM APIs (OpenAI/Anthropic/others).
• Strong backend engineering in Python (FastAPI/Django or equivalent) and high-volume, high-concurrency system design.
• Multi-cloud experience (AWS and/or GCP) with Terraform/IaC, CI/CD, and containerization (Docker/Kubernetes).
• Fluency across relational and non-relational databases and data-pipeline design.
• Sound judgment on where automation is appropriate and where human review must remain; strong attention to detail; high integrity with sensitive/confidential data.
• Ability to interpret a business problem, engage stakeholders, and lead delivery with minimal direction.

Nice to have

• MS in Machine Learning, Computer Science, or a related field; strong CS fundamentals (system design, data structures).
• Experience in financial services, investment management, or multi-entity/data-governance-heavy environments.
• Open-source contributions, published work, or a portfolio of production AI/data systems.
• Experience across distributed/international teams.