Senior Software Engineer, Applied AI

Syllo

18d•$160,000 - $200,000•Remote

About The Position

Syllo is seeking a skilled, fast-moving Applied AI Engineer to build practical, user-facing AI features, particularly those powered by large language models. This is an engineering-focused role centered on building and integrating robust production systems rather than conducting primarily research work. The engineer will own new AI features through their full lifecycle, from design and prototyping through API design, integration, data storage, deployment, monitoring, and alerting. The role also involves enhancing existing data and feature pipelines and collaborating with product managers and engineers to deliver features iteratively.

Requirements

Proven ability to build and deploy complex, high-quality software systems, with a focus on maintainable code, rigorous testing, and engineering best practices.
Fluency in Python and its ecosystem for backend services and data processing.
Strong understanding of system design, distributed systems, and API design, with demonstrated ability to design scalable distributed systems.
Commercial experience building, shipping, and maintaining AI-powered products, agents, or intelligent features.
Hands-on experience integrating LLMs into production, including prompt engineering, vector databases, retrieval-augmented generation (RAG), and context-window management.
Ability to quickly read, understand, and navigate an unfamiliar codebase.

Nice To Haves

Experience fine-tuning or distilling smaller task-specific models, with sound judgment about when it is worthwhile.
Familiarity with agent frameworks and their failure modes.
Familiarity with cloud platforms such as AWS, GCP, or Azure, and containerization tools such as Docker and Kubernetes.

Responsibilities

Design and build high-performance, reliable, scalable production AI features and services.
Develop engineering safeguards for LLM unreliability, including guardrails, validation pipelines, error handling, caching, and failover or fallback mechanisms.
Design long-running batch processing that is idempotent, resumable, and resilient to individual item failures.
Optimize latency, throughput, and cost efficiency for AI-powered services.
Integrate models and data feeds with existing business logic and APIs.
Define and implement evaluations of AI feature output quality, beyond system correctness.
Implement unit, integration, and performance testing strategies before and after deployment.
Maintain high standards for code quality, architecture, and documentation, and participate in peer code reviews.
Own the full lifecycle of AI features, including design, prototyping, API design, front-end service integration, persistent data storage, deployment, monitoring, and alerting.
Quickly learn the existing codebase and improve existing data and feature pipelines for efficiency and robustness.
Work with product managers and engineers to scope, estimate, and deliver features on a fast iterative cycle.