Staff AI Engineer

Kastle; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Competitive salary

Early-stage equity

Relocation support

Job summary

Kastle, based in San Francisco, is searching for a Founding Applied AI Engineer to shape its AI platform for consumer lending. You will integrate AI models, optimize performance, and ensure compliance with regulations. Your efforts will directly impact top mortgage lenders, enabling rapid deployment and real-world impact. This role demands a passion for applied AI and a collaborative spirit. Join a dynamic team of industry veterans and take an active role in building the future of lending with AI.

Qualifications

• 2+ years building and deploying ML/AI systems in production environments.
• Strong proficiency in Python and deep learning frameworks.
• Experience with LLM orchestration frameworks.
• Track record of shipping AI products that real users depend on.
• Strong product mindset and ability to translate business requirements into AI solutions.

Responsibilities

• Fine-tune and deploy LLMs for real-time voice-based borrower interactions.
• Design and iterate on prompt strategies to optimize AI performance and compliance.
• Build high quality evals to benchmark AI agent performance.
• Train and implement domain-specific AI models for consumer lending.
• Ensure AI solutions meet regulatory standards and scale efficiently.
• Build robust AI-driven workflows integrating with loan servicing platforms.
• Monitor performance metrics and continuously improve agent quality.

Skills

Building and deploying ML/AI systems

Proficiency in Python

Deep learning frameworks (TensorFlow, PyTorch)

LLM orchestration frameworks (LangChain, LlamaIndex)

Product mindset

Excellent communication skills

Job description

About Kastle

Kastle is building AI operating system for consumer lending, starting with mortgage. We work with some of America's largest mortgage lenders, helping them scale their contact center and compliance operations using AI-driven voice agents. Backed by Y Combinator, Commerce Ventures, and executives from Snapdocs, Google, and WePay, we are redefining lending with AI.

About the Role

As a Founding Applied AI Engineer, you'll be instrumental in building the technical foundation of Kastle's AI platform. You'll fine-tune large language models, design AI workflows for highly regulated enterprises, and ensure our voice agents deliver precise, compliant, and effective borrower interactions.

This role is ideal for an engineer who is passionate about applied AI, eager to solve real-world challenges, and excited to build the technical foundation of an early-stage AI startup.

What You'll Do

• AI Model Integration: Fine-tune and deploy LLMs for real-time voice-based borrower interactions
• Prompt Engineering: Design and iterate on prompt strategies to optimize AI performance and compliance
• Evaluate LLMs and AI Agents: Build high quality evals using our proprietary datasets to benchmark AI agent performance and run experiments
• Custom AI Solutions: Train and implement domain-specific AI models for consumer lending
• Scalability & Compliance: Ensure AI solutions meet regulatory standards (FDCPA, RESPA, TILA) and scale efficiently
• Data Pipelines & APIs: Build robust AI-driven workflows that integrate seamlessly with loan servicing platforms
• Continuous Optimization: Monitor performance metrics and continuously improve agent quality and borrower experience

What We're Looking For

• 2+ years building and deploying ML/AI systems in production environments
• Strong proficiency in Python and deep learning frameworks (TensorFlow, PyTorch)
• Experience with LLM orchestration frameworks (LangChain, LlamaIndex, or similar)
• Track record of shipping AI products that real users depend on
• Strong product mindset and ability to translate business requirements into AI solutions
• Excellent communication skills to collaborate across product, engineering, and compliance teams

Why join Kastle

Build what banks run on: Your code powers real borrower interactions at top-10 mortgage lenders—live in production from day one

Act like a founder: High ownership and autonomy with direct input on product, technical direction, and company culture

Learn fast: Daily customer exposure with rapid feedback loops—see your work deployed within days

Strong upside: Competitive salary, meaningful early-stage equity, and relocation support

Great team: Work alongside founders and engineers from Verkada, NVIDIA, Apple, Intuit, and Redfin.