Member of Technical Staff Applied ML

Member of Technical Staff (All Levels) - Applied ML

Join Basis to apply for the Member of Technical Staff (All Levels) - Applied ML role.

Basis equips accountants with a team of AI agents to take on real workflows. We have hit product‑market fit, have more demand than we can meet, and just raised $34 million to scale at a speed that meets this moment. Built in New York City.

We build the ML systems that power Basis’s AI Accountant. Our systems read documents, reason over context, and complete real accounting workflows safely and accurately. We focus on the whole system, not just the model. We optimize everything around it: tools, memory, retrieval, orchestration, and evaluation. We push model providers to their limits when needed and run experiments to learn quickly.

We work in small, focused pods alongside Platform, Product, and Accounting experts, thinking in systems and writing code that is observable, understandable, and built for continuous learning in production.

As an ML Engineer at Basis, you’ll own end‑to‑end projects that bring intelligence into production, acting as the Responsible Party (RP) for systems that help our agents reason, plan, and evaluate. You’ll scope, build, and deliver from first principles, with full autonomy to plan projects, define success, run experiments, and decide when a system is ready to ship.

• Design and iterate multi‑agent architectures that automate real accounting workflows.
• Build autonomy boundaries, tool usage, and fallback behaviors that make agents safe and reliable.
• Manage context and memory for coherence across steps; plan and execute agent loops with measurable success criteria.
• Route, evaluate, and optimize models under real‑world constraints (latency, cost, accuracy).
• Build scalable evaluation pipelines (offline and online) that run hundreds of experiments automatically.
• Define golden tasks, labeling strategies, and metrics that make performance measurable and comparable.
• Instrument the stack to detect regressions, track error patterns, and drive continuous improvement.
• Use data and experiments to drive product and architectural decisions.
• Build prompt stacks and instruction hierarchies to structure model reasoning.
• Create retrieval and indexing pipelines that surface relevant context efficiently.
• Parse messy documents into structured representations that agents can understand.
• Design guardrails and validation layers to keep behavior safe and predictable.
• Scope projects clearly, write concise specs and architecture docs that eliminate ambiguity.
• Build, test, and instrument systems end‑to‑end.
• Communicate progress clearly, share learnings, and collaborate with your pod.

NYC, Flatiron office – in‑person team.

• Scope, execute, and deliver systems from concept to production.
• Instrument everything, measure outcomes, and learn from data.
• Design clean abstractions for complex ML systems that others can build on.
• Make the whole team faster and better through clear interfaces and insights.
• Move fast, stay curious, and build with conviction and care.