Job Summary:
As an AI Solutions Engineer, you will play a crucial role in developing and deploying advanced software solutions using generative AI technologies. You'll work at the intersection of AI and enterprise systems, integrating large language models and retrieval-augmented generation techniques to build scalable and efficient applications.
Key Responsibilities
Software Development & Deployment
- Develop scalable software solutions leveraging generative AI technologies.
- Design and deploy solutions integrating LLMs and RAG into enterprise systems.
- Build modular AI components, ensuring seamless integration with existing systems.
Collaboration & System Design
- Work closely with architects and senior engineers to implement GenAI system designs.
- Adhere to established reference architectures and standards in AI development.
Component Development & CI/CD
- Contribute to the creation of reusable components, templates, and patterns.
- Implement and maintain CI/CD pipelines, focusing on reliability and scalability.
- Ensure observability of GenAI applications for continuous monitoring.
System Evaluation & Troubleshooting
- Participate in testing, evaluation, and performance tuning of AI systems.
- Optimize prompts and troubleshoot deployed applications to ensure stability.
Documentation & Knowledge Sharing
- Produce clear technical documentation for implemented solutions.
- Engage in knowledge sharing to foster team learning and improvement.
Continuous Learning & Improvement
- Stay updated with advancements in generative AI and apply new learnings.
- Contribute to other duties/projects as assigned by management.
Required Experience & Skills
- Proficiency in building and deploying GenAI applications with LLM APIs and frameworks.
- Hands-on experience with retrieval-augmented generation (RAG) and vector databases.
- Familiarity with agent-based systems and tool integrations.
- Experience with cloud platforms like AWS, Azure, or GCP, and containerized environments such as Docker and Kubernetes.
- Understanding of CI/CD pipelines and modern deployment practices.
- Exposure to model evaluation, prompt engineering, and performance optimization.
- Proven track record in contributing to shared engineering standards or frameworks.
- Experience in release management and CI/CD deployment best practices