Basis · 1 month ago
Member of Technical Staff (All Levels) - Applied ML
New York Office
Full-time
Onsite
Entry, Mid, Senior Level
$100K/yr - $300K/yrBasis is a company that equips accountants with AI agents to enhance their workflows. They are seeking an ML Engineer who will own end-to-end projects to bring intelligence into production, focusing on building and evolving agent systems, designing evaluation frameworks, and operating with full autonomy.
AccountingArtificial Intelligence (AI)Information Technology
Responsibilities
Build and evolve our agent systems
Design and iterate multi-agent architectures that automate real accounting workflows
Build in 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)
Design evaluation and experimentation frameworks
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, not just intuition
Engineer for context and retrieval
Build prompt stacks and instruction hierarchies that 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
Operate as an RP: plan, build, deliver
Scope your projects clearly. Write concise specs and architecture docs that eliminate ambiguity
Build, test, and instrument your systems end-to-end
Communicate progress clearly: what's built, what's learned, what's next
Work closely with your pod, teaching, unblocking, and sharing learnings as you go
Qualification
Required
Experience in building and evolving agent systems
Ability to design and iterate multi-agent architectures that automate real accounting workflows
Experience in managing context and memory for coherence across steps
Ability to route, evaluate, and optimize models under real-world constraints (latency, cost, accuracy)
Experience in building scalable evaluation pipelines (offline and online) that run hundreds of experiments automatically
Ability to define golden tasks, labeling strategies, and metrics that make performance measurable and comparable
Experience in instrumenting the stack to detect regressions, track error patterns, and drive continuous improvement
Ability to use data and experiments to drive product and architectural decisions
Experience in building prompt stacks and instruction hierarchies that structure model reasoning
Ability to create retrieval and indexing pipelines that surface relevant context efficiently
Experience in parsing messy documents into structured representations
Ability to design guardrails and validation layers to keep behavior safe and predictable
Experience in scoping projects clearly and writing concise specs and architecture docs
Ability to build, test, and instrument systems end-to-end
Strong communication skills to convey progress clearly
Company
Basis
Basis provides AI agents that automate accounting workflows for professionals.
Founded in 2023
11-50 employees
H1B Sponsorship
Basis has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2024 (2)
2022 (5)
2020 (1)
Funding
Current Stage
Early StageTotal Funding
$37.6MKey Investors
Khosla VenturesBetter Tomorrow Ventures
2024-12-17Series A· $34M
2023-10-18Seed· $3.6M
2023-03-20Pre Seed
Leadership Team
Matt Harpe
Co-Founder
Mitchell Troyanovsky
Co-Founder
Recent News
2025-08-15
Company data provided by crunchbase