Write efficient and maintainable code following best practices in software engineering.
Working with DevSecOps tools for deploying and versioning code.
Conduct thorough research and analysis of retrieval techniques, language models, and generative AI methodologies.
Collaborate with data engineers to ensure data pipeline efficiency and accuracy.
Continuously iterate and refine retrieval augmented generation (RAG) methods and processes based on experimentation, analysis, and feedback. This will include embedding, chunking, loading, and search algorithm setup.
Experiment with different retrieval strategies, including information retrieval, nearest-neighbor searches, or knowledge graph-based retrievals, to augment generative AI models.
Algorithm Optimization – Optimize and fine-tune AI models for performance, scalability, and accuracy.
Work closely with cross-functional teams, including product managers, data scientists, and software engineers, to understand requirements and deliver AI-driven solutions.
Present findings and insights to stakeholders and contribute to strategic decision-making.
Document AI models, algorithms, and processes thoroughly.
Prepare technical reports and presentations to communicate results and methodologies.
Stay up to date with the latest advancements in AI and machine learning technologies.
Participate in Agile ceremonies with the team to execute on prioritized projects and features.
Implement automated testing and monitoring techniques to ensure the accuracy and reliability of AI systems.
Requirements & Skills:
2+ years of experience in AI Engineering.
Strong programming skills in Python.
Familiar with building scalable AI Solutions within a modern technology stack which includes cloud services, data pipelines, databases, and other necessary tooling.
Familiar with CI/CD and test-driven development
Experience in building Restful APIs for AI models.
Familiar with of machine learning concepts (i.e. neural networks, optimization algorithms, evaluation metrics).
Familiar with Retrieval Augmented Generation (RAG) techniques
Familiarity with prompt engineering techniques, such as instruction design, template-based approaches, rule-based conditioning, or fine-tuning strategies.
Strong communication and collaboration skills.
Must be analytical, detail-oriented, and able to manage multiple projects simultaneously.
Experience working in an Agile Methodology.
Additional programming languages such as Node.js / TypeScript, C#, or Java
Demonstrated experience in developing and refining prompts for generative AI models, preferably in creative or text generation domains.
Experience with AWS Cloud.
Experience with building, deploying, and managing docker images.
