Back to search
About the Role
This is an applied ML engineering role at a Series B fintech company building agentic AI for accounting professionals. You'll own end-to-end projects — from architecture through production — designing the systems that help intelligent agents reason, plan, and evaluate themselves at scale. The work sits at the intersection of research-minded thinking and pragmatic engineering, and your output will directly shape how accounting workflows become smarter and more autonomous.
What You'll Do
Design and iterate multi-agent architectures that automate real-world accounting workflows end-to-end.
Encode autonomy boundaries, tool usage, and fallback behaviors to keep agents safe, reliable, and auditable.
Manage context and memory across multi-step agent loops with clearly defined success criteria.
Route, evaluate, and optimize model usage under production constraints including latency, cost, and accuracy.
Build scalable evaluation pipelines — offline and online — capable of running hundreds of experiments automatically.
Define golden tasks, labeling strategies, and metrics that make model and product performance measurable and comparable.
Instrument the stack to detect regressions, track error taxonomies, and drive closed-loop improvement.
Architect prompt stacks and retrieval pipelines; parse messy documents into structured representations for reasoning.
Design guardrails and validation layers to keep agent behavior safe and deterministic.
What We're Looking For
3+ years of AI/ML engineering experience building production systems or AI applications.
Deep expertise in Python and LLM/transformer-based systems.
Hands-on experience building end-to-end LLM-based agent applications including model orchestration, benchmarking, and evaluation frameworks.
Experience designing and running structured ML experiments — hypothesis framing, evaluation infrastructure, and iteration on measurable results.
Experience building retrieval and indexing pipelines; familiarity with parsing unstructured documents into structured representations.
Background at a fast-paced startup, top-tier tech or AI-native company, or quantitative finance environment.
Strong CS fundamentals; a degree in CS, Math, Physics, or a related technical discipline.
Clear, concise communicator who can break complex concepts down to first principles.
Interest in AI applications within accounting, finance, or economic systems is a plus.
Compensation & Benefits
Salary range: $175,000 – $300,000 USD annually. Visa sponsorship is available.
Location
On-site, five days a week in Los Angeles, CA. Candidates currently located in the US or Canada preferred.
Learn more about this Employer on their Career Site
