Generative AI Engineer

Prosum; Fort Worth (TX); On-site; USD 140,000 - 210,000; Full time

Job summary

Prosum is seeking a highly skilled Generative AI Engineer to lead end-to-end delivery of production-grade AI systems in a Fort Worth environment. You will design, build, deploy, and optimize GenAI solutions that integrate with enterprise data and APIs.

You will set engineering standards for prompts, orchestration, and CI/CD; mentor teams; and drive innovation while ensuring security, reliability, and cost efficiency.

Qualifications

• Proven experience building production-grade LLM or generative AI systems.
• Strong prompt design, orchestration, and model tradeoffs.
• Experience developing evaluation frameworks for AI outputs.
• Background in distributed systems and production software engineering.
• Experience with CI/CD pipelines, release management, and ownership.
• Ability to define technical standards and influence architecture decisions.
• Experience with cloud-native systems, APIs, and event-driven architectures (Azure or similar).
• Bachelor's degree in a technical field or equivalent practical experience.

Responsibilities

• Own the full lifecycle of generative AI systems from architecture to deployment.
• Design and build LLM-powered applications and enterprise AI solutions.
• Establish engineering standards for prompts, orchestration and outputs.
• Lead GenAI architecture decisions and best practices.
• Integrate AI with enterprise data, APIs and cloud services.
• Evaluate models, optimize latency, cost, and performance.
• Build observability and CI/CD pipelines with release processes.
• Lead incident response and long-term fixes.
• Develop evaluation pipelines for LLM outputs and failure analysis.
• Implement safeguards like human-in-the-loop and schema validation.

Skills

LLM systems

Generative AI

Prompt design

Distributed systems

AI evaluation frameworks

Cloud-native architectures

Python

CI/CD

Education

Bachelor's degree in a technical field

Tools

Python

Azure

Docker

Kubernetes

Terraform

Git

Job description

We are seeking a highly skilled Generative AI Engineer to lead the end-to-end delivery of production-grade AI systems. This role is responsible for designing, building, deploying, and continuously optimizing scalable generative AI solutions that integrate seamlessly with enterprise systems. You will act as a technical authority, shaping best practices and driving innovation across AI initiatives.

What You'll Do

• Own the full lifecycle of generative AI systems, from architecture and development to deployment, monitoring, and optimization
• Design and build LLM-powered applications, including agent-based workflows, multi-step RAG pipelines, and enterprise AI solutions
• Establish and enforce engineering standards across prompt design, orchestration, structured outputs, and workflow lifecycle management
• Serve as a technical leader for GenAI, guiding architecture decisions and best practices
• Integrate AI systems with enterprise data, internal APIs, and cloud-native services
• Evaluate and select models, implement routing strategies, and optimize for latency, cost, and performance
• Continuously assess emerging AI tools and improve existing systems
• Own system performance across reliability, scalability, throughput, and cost efficiency
• Build and maintain observability frameworks (monitoring, tracing, logging, alerting)
• Design and manage CI/CD pipelines, including versioning and release processes
• Lead incident response and root cause analysis, implementing long-term fixes
• Develop evaluation pipelines for LLM outputs, including regression testing and failure analysis
• Implement safeguards such as human-in-the-loop workflows, schema validation, and output controls
• Ensure systems are secure against prompt injection, data leakage, and unauthorized access
• Collaborate with leadership and cross-functional teams to define and execute AI initiatives
• Provide hands‑on technical guidance, mentoring, and code reviews
• Promote iterative delivery with frequent releases and continuous feedback loops

Required Qualifications

• Proven experience building and deploying production-grade LLM or generative AI systems
• Strong expertise in prompt design, orchestration, and model tradeoffs
• Experience developing evaluation frameworks for AI outputs and validating quality
• Solid background in distributed systems and production software engineering
• Experience with CI/CD pipelines, release management, and operational ownership
• Demonstrated ability to define technical standards and influence architecture decisions
• Experience with cloud-native systems, APIs, and event-driven architectures (Azure or similar)
• Experience integrating AI solutions with enterprise data and security requirements
• Bachelor's degree in a technical field or equivalent practical experience

Preferred Qualifications

• Experience with advanced RAG pipelines and agent-based AI systems in production
• Familiarity with cloud AI services and modern infrastructure tooling
• Experience with Python-based AI frameworks and data pipelines
• Experience with containerization and deploying AI workloads
• Knowledge of responsible AI practices and governance
• Domain experience in areas such as product data, ERP, ecommerce, or analytics platforms