Software Engineer, AI/ML

Interfere•New York, NY

105d•$160,000 - $250,000•Onsite

About The Position

Interfere is building a product-quality platform that detects real-time user failures and gives product teams the context needed to identify and fix them. The company is a seven-person team in New York with $5.1 million raised, and its product is already running in production with design partners. The Software Engineer, AI/ML will own the intelligence layer behind the product, building agents, evaluations, and inference pipelines that determine what is broken, why it happened, and what to do about it. The role combines research and production engineering, shipping systems that operate at scale against real codebases and runtime data. Work includes agents that investigate codebases, traces, logs, and runtime behavior; LLM pipelines for triage, root-cause analysis, and fix proposals; anomaly detection; evaluation and feedback infrastructure; context engineering and integrations; and systems that learn from bugs found and fixed. The team works in person in New York City, ships daily, and measures work by outcomes rather than hours. Employees are expected to own substantial features and subsystems, work with urgency, and take responsibility for adjacent problems they discover.

Requirements

Have shipped ML- or LLM-powered systems into production for real users.
Move comfortably between research and engineering and learn unfamiliar technologies quickly.
Be able to prototype new techniques and frameworks, then evaluate whether they improve results.
Be able to own ambiguous 0-to-1 work from beginning to end without waiting for a fully specified plan.
Treat evaluations as a first-class engineering responsibility and measure system performance.
Have production experience with agent architectures, tool use, multi-step reasoning, or autonomous workflows.

Nice To Haves

Background in code understanding, program analysis, or systems that reason over source code.
Experience building retrieval, RAG, or context-construction systems for large or messy datasets.
Experience with anomaly detection, time-series modeling, or learned monitoring systems.
A strong understanding of the inner workings of AI/ML systems.

Responsibilities

Build agents that reason about codebases, traces, logs, and runtime behavior to find and explain bugs, including their sandboxes and the browsers and web research used for investigations.
Develop LLM pipelines for triage, root-cause analysis, and automated fix proposals, including model routing.
Build systems to detect anomalies in product behavior, performance, and user experience across noisy real-world data.
Create evaluations, datasets, observability, and feedback loops to measure and improve system performance.
Architect standards for the agentic components of a product whose category and capabilities are still being defined.
Build context-engineering systems that help models understand customer codebases, including retrieval, indexing, context construction, and integrations.
Develop systems that use bugs found and fixed as signals to improve future detection.
Own AI problems from definition through implementation and delivery, while identifying and addressing related problems.