Senior AI Engineer – Agentic AI & LLM Production Systems

Senior AI Engineer – Agentic AI & LLM Production Systems

Onsite - Dallas, TX

About the Role

We are seeking an experienced AI Engineer with strong expertise in Python, production ML systems, LLMs, and Agentic AI. The role focuses on building secure, scalable AI agents and RAG pipelines to automate production operations, diagnostics, incident management, and remediation.

Roles & Responsibilities

• Design and build agentic AI systems using tool calling, structured reasoning, secure action execution, and the MCP protocol.
• Implement safety guardrails, policy enforcement, and least-privilege access controls.
• Productionize LLMs by building evaluation frameworks, retrieval pipelines, prompt synthesis, response validation, and self-correction loops.
• Integrate AI agents with observability, incident management, deployment systems, and operational runbooks.
• Build RAG pipelines, validate data quality, and maintain knowledge freshness.
• Implement validator models, adversarial prompts, policy checks, deterministic fallbacks, and rollback strategies.
• Optimize AI application cost, latency, context management, caching, and model routing.
• Collaborate with production engineers and application teams to identify operational challenges and deliver measurable business outcomes.
• Establish continuous evaluation for accuracy, usefulness, reliability, and risk.
• Lead design reviews, promote engineering best practices, and mentor peers on agent architectures and safe AI deployment.

Required Skills & Experience

• 10+ years of software development experience in Python, C/C++, Go, or Java; strong Python application development preferred.
• 3+ years designing, testing, and deploying production ML systems, including model serving, evaluation, monitoring, data pipelines, and fine-tuning.
• Hands-on experience with LLM APIs, prompt engineering, fine-tuning/adaptation, RAG, vector retrieval, function calling, and tool-using agents.
• Understanding of commercial and open-source LLMs, including OpenAI, Gemini, Llama, Qwen, and Claude.
• Experience building secure, reliable, and scalable AI-powered applications.
• Strong understanding of applied statistics, core ML concepts, algorithms, and data structures.
• Strong analytical, problem-solving, communication, and collaboration skills.
• AWS cloud infrastructure experience.
• Experience with ECS/EKS, Lambda, S3, DynamoDB, Redshift, Step Functions, and SageMaker.
• Infrastructure-as-code experience with Terraform or CloudFormation.

Benefits (W2)

• Health insurance
• Health savings account
• Dental insurance
• Vision insurance
• Flexible spending accounts
• Life insurance
• Retirement plan

EEO Statement

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran.