As a Machine Learning Software Engineer at PermitFlow, your responsibilities include designing, implementing, and optimizing LLM-powered models focused on document processing and data extraction. You'll also develop and fine-tune retrieval-augmented generation (RAG) pipelines, ensuring that complex permitting data is efficiently managed and retrieved. Collaborating with cross-functional teams, you’ll help create AI-native solutions that address real-world challenges in the construction permitting process.

To qualify for the Machine Learning Software Engineer role at PermitFlow, you should have at least 3 years of experience in machine learning engineering within production environments. A profound understanding of LLMs and their applications is essential, alongside experience with retrieval systems. Proficiency in Python and common machine learning libraries is required, as well as direct experience with model deployment in cloud environments like AWS, GCP, or Azure.

At PermitFlow, you'll work with cutting-edge technologies, including LLMs such as OpenAI GPT and models from Hugging Face. You'll also utilize retrieval systems like Elasticsearch and FAISS, conducting experiments with pre-trained models for NLP tasks such as document classification and entity recognition. Your work will involve creating scalable machine learning infrastructure, integrating seamlessly with our backend systems.

Absolutely! PermitFlow values diverse perspectives and backgrounds in the workplace. We look for passion and excitement about joining our team, regardless of your previous experiences. If you're motivated to tackle significant challenges in the construction industry and eager to make an impact, we encourage you to apply, regardless of your background.

The work culture at PermitFlow promotes a fast-paced, high-ownership environment, fostering collaboration and personal growth. As part of our small yet mighty engineering team, you will enjoy the opportunity to take ownership of projects while working closely with talented individuals from various industries. We also support work-life balance with a hybrid schedule, providing an engaging and inclusive atmosphere for all team members.

When discussing your experience with LLMs, focus on the specific projects you’ve worked on that utilized such models. Highlight techniques you've employed, challenges faced, and how your contributions improved performance or efficiency. Be sure to mention any specific applications relevant to document processing or NLP tasks.

Describe your methodology when optimizing machine learning models. You can highlight techniques like hyperparameter tuning, using cross-validation, or implementing various evaluation metrics. Providing examples of past models you optimized and the impact of your strategies can make your answer more compelling.

Discuss your specific experience with services from AWS, GCP, or Azure for deploying machine learning models. Focus on how you ensure scalability and reliability in a production environment, the tools you prefer for monitoring, and any strategies for maintaining model performance over time.

When answering this question, detail the problem you faced, the computational methods or algorithms you applied, and how you arrived at a solution. Highlight any quantitative results that came from your work, demonstrating your problem-solving ability and technical proficiency.

Be specific about your hands-on experience with retrieval systems like Elasticsearch. Mention projects where you implemented these systems, the challenges you faced, and how you integrated them into larger workflows or applications, focusing on their impact on information retrieval and query processing.

Demonstrate your commitment to continuous learning. Discuss the platforms, journals, or conferences you follow to stay informed. Mention workshops or online courses you've completed recently that relate to LLMs, NLP, or AI-driven automation to showcase your proactive approach to professional development.

Describe the validation techniques you use to gauge the accuracy of your models, such as cross-validation, confusion matrices, or A/B testing. Discuss any instances where you had to diagnose and adjust models based on false positives or negatives, detailing the steps you took to improve accuracy.

Collaboration is key in engineering roles. Explain how you communicate with product managers, designers, and engineers to ensure alignment on project goals. Discuss any specific tools or practices you’ve implemented to enhance teamwork and ensure that everyone is on the same page throughout the development process.

Highlight your experience with large datasets and the strategies you've employed to manage and process them effectively. Discuss transformations, cleaning methods, or indexing techniques you've used to ensure data integrity and accessibility, especially in relation to machine learning projects.

Talk about the monitoring tools and metrics you use to assess performance after deployment. Discuss how you handle model drift and the strategies you have in place for retraining or optimizing models based on real-world feedback and usage data.