Job Description

Position Overview

As a Staff Software Engineer, AI, you will play a key role in designing, building, and maintaining AI-powered enterprise applications. You will work closely with product managers, designers, and engineers to deliver innovative software solutions that solve high-stakes problems for our customers. Your primary focus will be on Screens, an AI-powered contract review application, where you will apply cutting-edge techniques using LLMs, RAG, and AI agent frameworks. You will also contribute to improving internal AI tooling, driving best practices, and mentoring team members.

• Design, build, and maintain AI-driven enterprise applications, with a focus on integrating and optimizing commercial and open source LLM APIs
• Evaluate and implement RAG pipelines, agent architectures, and fine-tuned model solutions
• Partner with product managers and designers to identify AI opportunities, brainstorm solutions, and deliver intuitive, high-quality user experiences
• Develop and maintain robust backend services and APIs to support AI-powered features, ensuring scalability and reliability
• Continuously improve AI model evaluation processes and system performance, focusing on accuracy, latency, and cost-efficiency
• Enhance internal AI developer tools, workflows, and infrastructure to increase productivity and streamline AI experimentation
• Lead efforts to establish AI engineering best practices, including prompt engineering, evaluation frameworks, and error handling for AI systems
• Troubleshoot and resolve complex issues across the AI and application stack, ensuring high availability and fault tolerance
• Participate in incident response, disaster recovery efforts, and ongoing system monitoring
• Other duties as assigned

• Bachelor’s degree in Computer Science, Information Technology, or a related field (or equivalent experience)
• Minimum 5+ years of professional experience as a software engineer, with 3+ years of applied AI/ML experience
• Proven experience integrating commercial LLM APIs (OpenAI, Anthropic, or similar) into modern software applications
• Strong knowledge of building cloud-native applications using serverless technologies (API Gateway, Lambda, DynamoDB or similar)
• Deep understanding of AI model evaluation, prompt engineering, and RAG techniques
• Strong problem-solving skills with a solid understanding of system architecture, distributed systems, and performance optimization
• Familiarity with AI agent frameworks, evaluation methodologies, and benchmarking tools
• Hands-on experience building RAG-based systems, working with vector databases, and AI evaluation pipelines
• Excellent collaboration, teamwork, and communication skills
• Eagerness to stay up to date with the latest AI advancements

• Exposure to cutting-edge agentic frameworks, LLM chaining, or other complex LLM workflows
• Experience with fine-tuning commercial or open source LLMs
• Proficiency in Infrastructure as Code with AWS (CloudFormation, SAM, or Terraform)
• Hands-on experience with traditional data science and machine learning techniques
• Comfortability with data science tooling in Python (numpy, scipy, scikit-learn, pandas) to support AI experimentation
• Experience with CI/CD pipelines and DevOps practices using GitHub Actions or similar
• Knowledge of containerization and orchestration using Docker and ECS

Job Tags

Similar Jobs