AI Engineer – Open-Source AI Integration

Entech; Malvern (Chester County); Hybrid; USD 110,000 - 170,000; Full time

Job summary

Entech is seeking a hands-on AI Engineer to support a proof of concept using self-hosted, open-source AI to enhance quality assurance. This role will configure AI platforms and integrate them with ALM/QC, Jira, Selenium, and SDLC tools to support requirements review, test generation, code review, and defect triage.

Primarily remote, with occasional onsite work in Malvern, PA. The six-month+ engagement offers potential extension as the project evolves and scales.

Qualifications

• Hands-on experience deploying open-source LLMs and configuring self-hosted AI platforms.
• Experience integrating ALM/QC, Jira, Selenium, and enterprise systems.
• Working knowledge of AI agents, RAG, vector databases, and workflow orchestration.
• Strong QA automation skills, including Selenium, scripting, test generation, and defect management.
• Practical experience applying AI to QA or SDLC workflows and measuring output quality.

Responsibilities

• Deploy and configure self-hosted LLMs on Azure using containers or VMs and runtimes such as Ollama or vLLM.
• Build AI agents and workflows using orchestration tools such as n8n, RAG, and vector databases.
• Integrate QA and SDLC tools through APIs, webhooks, and connectors; troubleshoot authentication and data-flow issues.
• Evaluate AI accuracy, performance, compute costs, and QA productivity against established baselines.
• Partner with the AI Architect on model selection, retrieval, security, and scalability.

Skills

LMM deployment

QA automation

Selenium

Python scripting

AI integration

Open-source tooling

Tools

Docker

Kubernetes

Azure

Ollama

vLLM

n8n

vector databases

Job description

Engagement: 6+ months, could go long term

Location: Primarily remote, with occasional onsite work in Malvern, PA

Entech is seeking a hands-on AI Engineer to support a proof of concept using self-hosted, open-source AI to enhance quality assurance. This role will configure AI platforms and integrate them with existing ALM/QC, Jira, Selenium, and SDLC tools to support requirements review, test generation, code review, and defect triage.

Key Responsibilities

• Deploy and configure self-hosted LLMs on Azure using containers or VMs and runtimes such as Ollama or vLLM.
• Build AI agents and workflows using orchestration tools such as n8n, RAG, and vector databases.
• Integrate QA and SDLC tools through APIs, webhooks, and connectors; troubleshoot authentication and data-flow issues.
• Evaluate AI accuracy, performance, compute costs, and QA productivity against established baselines.
• Partner with the AI Architect on model selection, retrieval, security, and scalability.

Required Qualifications

• Hands-on experience deploying open-source LLMs and configuring self-hosted AI platforms.
• Experience integrating ALM/QC, Jira, Selenium, and enterprise systems.
• Working knowledge of AI agents, RAG, vector databases, and workflow orchestration.
• Strong QA automation skills, including Selenium, scripting, test generation, and defect management.
• Practical experience applying AI to QA or SDLC workflows and measuring output quality.

Preferred Qualifications

• Experience with GitLab, CI/CD pipelines, and code-scanning tools.
• Experience delivering AI proofs of concept and measuring automation ROI.