AI Product Engineer (Backend/LLM)
We're a team of driven, enthusiastic problem solvers with strong backgrounds in machine learning, engineering, product management, legal and operations, on a mission to help attorneys resolve cases faster, for better outcomes. We're combining cutting edge models, approaches, and technologies with precise human in loop and data annotation processes. After achieving state-of-the-art results in automatic transcription, we're now pushing the boundaries in advanced NLP problems such as summarization of medical records and legal depositions, or automations of other legal workflows. We have many challenges to solve, which is exactly where you'll start if you join us.
As an AI Product Engineer, you will work closely with Machine learning Engineers, turning AI capabilities into dependable product features. You will own the systems and workflows that make AI-powered customer experiences reliable, secure, measurable, and maintainable.
Key responsibilities
Own AI-powered features from technical design and implementation through rollout, monitoring, and maintenance
Design services, APIs, data pipelines, and workflows that integrate LLMs and other machine-learning capabilities into Filevine products
Turn prototypes into production systems weith appropriate reliability, scalability, security, latency, and cost
Implement patterns such as retrieval and grounding, structured generation, tool use, human review, and graceful fallbacks
Establish quality metrics, tracing, monitoring, and feedback loops for AI-powered features
Collaborate with ML Engineers, Software Engineers, Product, and domain experts to turn customer problems into practical solutions
Make pragmatic technical decisions and communicate their context and tradeoffs clearly
Who are we looking for
At least 5 years of professional software-engineering experience, including end-to-end ownership of production systems
Experience designing, delivering, and operating AI-powered product functionality in production
Strong software-engineering foundations, including API design, data modeling, distributed systems, testing, and failure handling
Strong experience with Python or a comparable language and the ability to work in a Python-first environment
Practical understanding of production LLM systems, including retrieval, context management, structured outputs, tool calling, evaluations, guardrails, and common failure modes
Experience with asynchronous workflows, data-processing pipelines, background jobs, or event-driven systems
Experience deploying and operating cloud services; our stack includes Python, TypeScript, Temporal, Kubernetes, and AWS
Ability to evaluate tradeoffs among quality, reliability, latency, user experience, complexity, and cost
Good communication and writing skills in English, team spirit, and an independent problem-solving mindset
Ability to meet periodically in our Prague or Bratislava office, as we value in-person collaboration