AI Data Integration Engineer

Valiant Technologies LLC; San Jose (CA); On-site; USD 91,000 - 124,000; Full time

Job summary

Valiant Technologies LLC in San Jose, CA is seeking an AI Data Integration Engineer to turn legacy schemas into first-pass mapping specs and ensure clean, production-ready data flows.

You will design architectures for connecting internal and external systems, apply AI-assisted mapping and data quality checks, and build robust ETL pipelines with SQL, REST and SOAP APIs to feed our central platform while maintaining HIPAA compliance.

Qualifications

• Minimum 5 years in data/integration or ETL engineering for production systems.
• Healthcare/RCM experience preferred; exposure to PM systems.
• Experience using AI/LLM APIs for schema inference and data quality checks.
• Production-grade SQL proficiency and API design experience.
• Knowledge of HIPAA security practices and PHI handling.

Responsibilities

• Lead architectural design of integration strategies connecting internal and external systems.
• Apply AI-assisted mapping and data quality checks to accelerate schema alignment.
• Model data and create source-to-target mapping specs for PM systems to AI platform.
• Design ETL pipelines and REST/SOAP APIs to move data into Resolv Core.
• Wrangle data into target formats and document models and pipelines.
• Maintain reliability by monitoring and resolving production integration issues.
• Collaborate with AI Architect, product, engineering, ops, and leadership.
• Document data models, mappings, and pipeline configurations.

Skills

AI/LLM usage

Data modeling

Data quality checks

Cloud integration concepts

HIPAA security awareness

Tools

SQL

REST API design

SOAP API design

Azure Data Factory

ETL pipelines

Job description

US Citizen, Green Card, H-1B, OPT-EAD, CPT, Other

Job Title: AI Data Integration Engineer
Location: San Jose, CA
Duration: 12 Months + Extension
Bill Rate: $78/hour (C2C)
Job Type: W-2, 1099, C2C
Client: To Be Discussed Later
Work Authorization: US Citizen, Green Card, OPT-EAD, CPT, H-1B, H4-EAD, Other

Job Summary:
You'll use it to turn raw legacy schemas and documentation into first-pass mapping specs, reconcile inconsistent field names and codes across systems, and catch data-quality problems that manual review would miss before they hit production.

Key Responsibilities:

• Lead the architectural design of integration strategies and solutions that connect various internal and external systems to our central platform.


• AI-accelerated mapping & data quality: use AI/LLM tools to speed up schema mapping, field reconciliation, and anomaly detection.


• Data modeling & mapping: build data models and source-to-target mapping specs from Practice Management (PM) systems to our AI platform.


• Pipelines: design and build ETL processes and REST/SOAP APIs that move data into Resolv Core, per the architect's design.


• Data wrangling: cleanse, structure, and enrich source data into Resolv Core's target format.


• Pave the path where there's no existing playbook; several of these legacy systems are poorly documented.


• Reliability: monitor, troubleshoot, and resolve integration issues in production.


• Collaboration: work closely with our AI Architect, product, engineering, operations, and leadership.


• Documentation: maintain data models, mapping specs, and pipeline configurations.

Qualifications:

Experience: A minimum of 5 years in data/system integration or ETL engineering, building production integrations against complex legacy systems.

Healthcare/RCM experience preferred; direct exposure to one or more Practice Managenent (PM) systems.

Technical (AI first):

• Hands-on experience using AI/LLM APIs (e.g., OpenAI, Azure OpenAI) for schema inference, field-mapping/entity resolution, or automated data-quality checks - with concrete examples.


• Judgment on the best approach to using AI tooling.


• Production-grade proficiency with SQL and experience with relational databases.


• Design, build, and maintain ETL processes, data pipelines, and APIs to facilitate the seamless flow of data between different applications and data sources.


• REST and SOAP API development.


• Comfortable with JSON, XML, CSV, flat-file, and EDI formats.


• Data modeling and mapping-spec authorship.


• Understanding of HIPAA and PHI security practices.


• Cloud integration platforms; Azure stack (Fabric, Data Lake, SQL, Data Factory) a plus.

We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.