AI Platform Engineer

Innova Software Services Inc.

Dallas, TX, United States

4 days ago

Apply on www.indeed.com

Prepare application

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Experienced

Experience required

3 years minimum

Working hours

Regular working hours

Job source

www.indeed.com

Tech stack

Artificial Intelligence Amazon Web Services Amazon Elastic Compute Cloud Amazon S3 Bash Shell Software as a Service Cloud Computing Computer Programming DevOps Programming Tools Github Identity and Access Management

+14 more

Python (Programming Language) Systems Development Life Cycle Reliability Engineering Cloud Services Software Deployment Software Engineering TypeScript AWS Cdk Scripting Large Language Models Prompt Engineering AI Platforms Machine Learning Operations Terraform

Job description

We are seeking an AI-focused Platform Engineer to join the Platform Engineering team. This role will focus on designing, building, and operating internal platforms and tooling that support engineering teams across the organization.

The ideal candidate is not simply an engineer who uses AI, but someone who builds with AI. You will integrate Large Language Models (LLMs) and AI agents into engineering workflows, establish AI-assisted and spec-driven development practices, automate the software development lifecycle (SDLC), and help scale modern AI-enabled developer tooling., * Integrate LLMs and AI agents into core engineering workflows to improve developer velocity and reduce cognitive load.

Implement and scale spec-driven development practices using tools such as Claude / Claude Code, GitHub Spec-Kit, or equivalent solutions.
Maintain, optimize, and scale internal developer platforms with a focus on availability, security, reliability, and performance.
Architect and manage cloud infrastructure, predominantly within AWS.
Ensure seamless integration between cloud services, developer platforms, and AI tooling.
Own projects from concept through production deployment.
Work independently in a fast-paced, agile engineering environment.
Collaborate with cross-functional engineering teams to identify pain points and opportunities for automation.
Promote AI-assisted development best practices across engineering teams.
Develop internal documentation and provide training related to AI-enabled development workflows.

Requirements

3+ years of experience in Platform Engineering, DevOps, Site Reliability Engineering (SRE), or a related role.
Strong experience building internal developer platforms and tooling.
Hands-on experience with LLM APIs, prompt engineering, AI agents, or AI-assisted coding tools.
Familiarity or direct experience with modern AI development frameworks and spec-driven development.
Experience with Claude / Claude Code, GitHub Spec-Kit, Copilot Workspace, or similar tools.
Strong knowledge of AWS, including services such as:
IAM
EC2
ECS/EKS
Lambda
S3
RDS
Experience with Infrastructure as Code (IaC) using Terraform, AWS CDK, or similar technologies.
Strong programming/scripting skills in one or more of:
Python
Go
TypeScript
Bash
Strong problem-solving skills with the ability to work through ambiguity and shifting priorities.
Ability to deliver clean, production-grade code efficiently.

Preferred Qualifications

Advanced experience configuring, fine-tuning, or maximizing the organizational value of Claude / Claude Code or similar enterprise AI coding assistants.
Experience developing internal GUI tools, developer portals, or IDE extensions.
Knowledge of MLOps practices.
Experience with vector databases such as Pinecone, Milvus, or pgvector.
Previous experience within FinTech, regulated SaaS, or another highly regulated technology environment.