Senior Software Engineer, Applied AI

Senior Software Engineer, Applied AI

About Syllo 

Syllo is on a mission to transform litigation. Our product is a unified litigation platform that enables lawyers and paralegals to safely harness the power of language models and agentic AI throughout the litigation life cycle. Since going to market, we have gained a diverse group of enterprise customers, including some of the biggest law firms and corporations in the country, and we are quickly expanding. By reducing the expense of litigation industry-wide, we aim to improve access to high-quality representation and promote the alignment of legal outcomes with merit. 

About the Role

We are seeking a skilled and fast-moving Applied AI Engineer to join our team. This role is focused on the practical application of AI, specifically leveraging Large Language Models (LLMs), to build robust, scalable, and impactful user-facing features. This is an engineering-centric role. You will be an expert at building and integrating production systems, not primarily a research scientist.

Responsibilities 

• Design and build high-performance, production-level AI-powered features and services, with a focus on reliability and scalability.
• Develop robust engineering solutions to mitigate the inherent unreliability of LLMs. This includes implementing effective guardrails, validation pipelines, error handling, caching, and failover/fallback mechanisms to ensure a high-quality user experience even when the model misbehaves.
• Design long-running batch processing that is idempotent, resumable, and resilient to individual item failures.
• Focus on optimizing latency, throughput, and cost efficiency for all AI-powered services.
• Serve as an engineering expert in integrating models and data feeds with existing business logic and APIs.
• Define and implement evaluation for AI feature output quality, not only system correctness.
• Implement rigorous testing strategies, including unit, integration, and performance testing, to ensure the robustness of AI features before and after deployment.
• Champion and enforce high standards for code quality, architectural design, and system documentation, and participate actively in peer code reviews to maintain a high bar across the team.
• Take ownership of the full lifecycle of new AI features, from initial design and prototyping through API design, integration with front-end services, persistent data storage, deployment, and comprehensive monitoring and alerting.
• Quickly onboard onto our existing codebase to understand, maintain, and significantly enhance existing data and feature pipelines, improving their efficiency and robustness.
• Work closely with product managers and other engineers to scope, estimate, and deliver features on a fast iterative cycle.

Qualifications 

• Deep Engineering Fluency and Quality Focus: Proven ability to build and deploy complex, high-quality software systems with an emphasis on maintainable code, rigorous testing, and engineering best practices.
• Python Proficiency: Fluent in Python and its ecosystem for backend services and data processing.
• System Design Expertise: Strong grasp of system design principles, including distributed systems and API design, and demonstrated ability to design scalable distributed systems.
• AI/ML Feature Experience: Experience directly building, shipping, and maintaining AI-powered products, agents, or intelligent features in a commercial setting.
• LLM Production Experience: Hands-on experience with the engineering challenges of integrating Large Language Models into a production environment, including prompt engineering, working with vector databases, RAG systems, and managing context windows.
• Codebase Agility: Excellent ability to read, understand, and navigate an unfamiliar codebase quickly.

Great to Have

• Experience fine-tuning or distilling smaller task-specific models, and judgment about when that is worth doing.
• Familiarity with agent frameworks and their failure modes.
• Familiarity with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes) for deploying and managing services.