The team builds production AI systems for an enterprise process intelligence platform.
Your work turns messy customer data into reliable, structured insights using hosted frontier models.
Responsibilities
Build and maintain AI services and pipelines for retrieval, context construction, model selection, structured extraction, orchestration, and monitoring.
Own those services from design through production.
Create evaluations and representative datasets to measure quality, find failure causes, and catch regressions.
Make systems more reliable with guardrails, verification, retries, fallback paths, and production observability.
Turn customer feedback into product improvements and keep users informed.
Work across the full path from raw enterprise data to model outputs and what users see in the product.
Requirements
Typically 5 to 10 years of experience building production software, applied AI, or ML systems.
Strong Python skills, including running services and using asynchronous patterns.
Familiarity with a typed language such as Go, Java, C++, Scala, or C is a plus.
Hands-on work with hosted LLM APIs, structured outputs, retrieval-augmented generation, tool use, or multi-step workflows.
Experience building AI evaluations, benchmarks, regression tests, or CI/CD workflows, and running reliable, observable services in production.
Practical knowledge of retrieval systems such as embeddings, hybrid search, chunking, ranking, or reranking.
Experience with agent workflows or enterprise document understanding is valuable.
Experience shipping AI features to external enterprise customers, acting on customer feedback, and owning large projects end to end.
Comfort in an early-stage or startup setting, working through ambiguity and making pragmatic build-versus-buy calls.
A bachelor's degree or higher in computer science, engineering, or a related technical field.
Experience with process intelligence or workflow systems and multimodal enterprise data is a plus.
Conditions
Base salary ranges from $180,000 to $275,000 per year.