AI/ML Engineer: Production Pipelines & RAG

Tech Economy; Houston (TX); Hybrid; USD 83,000 - 91,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Tech Economy seeks an AI/ML Engineer to build and maintain production data and ML pipelines, collaborating with Data Engineers and Data Scientists to deliver RAG-based solutions. You will own components of ingestion, embedding, and retrieval stacks, delivering reliable, testable code from day one.

The role emphasizes production-quality Python, performance observability, and working within a hybrid model requiring in-office presence at least one day per week.

Qualifications

• Bachelor’s degree or equivalent practical experience in a relevant field.
• 2+ years building software, data, or ML systems; production pipelines experience preferred.
• Exposure to model deployment, serving, or monitoring is a plus.
• Experience collaborating with Data Engineers, Data Scientists, or the Agent / AI squad to ship features relying on retrieval or ML outputs.

Responsibilities

• Implement and maintain components of production data and ML pipelines under senior engineers.
• Build and support RAG and retrieval stack: chunking, embeddings, indexing into pgvector, and basic retrieval/logistics.
• Write production-quality Python with type hints, tests, and linting; code reviewed before merge.
• Instrument pipelines with logs/metrics and help build dashboards/alerts for observability.
• Triage, reproduce, and fix bugs in pipelines and serving code with escalation to seniors as needed.

Skills

Python

Data pipelines

ML pipelines

RAG

Code reviews

Git

Communication

Education

Bachelor’s degree in Computer Science, Engineering, Machine Learning, Data Science, Statistics, or related field

Tools

Docker

LangChain

LlamaIndex

pgvector

Databricks

Azure

AWS

Pytest

Ruff

Pydantic

MLflow

Portkey

Job description

Tech Economy seeks an AI/ML Engineer to build and maintain production data and ML pipelines, collaborating with Data Engineers and Data Scientists to deliver RAG-based solutions. You will own components of ingestion, embedding, and retrieval stacks, delivering reliable, testable code from day one.

The role emphasizes production-quality Python, performance observability, and working within a hybrid model requiring in-office presence at least one day per week.