Member of Technical Staff - Applied ML

About the Role

This is an applied ML engineering role on the core agent team at a Series B fintech company building AI-powered automation for accounting professionals. You will own end-to-end projects, from first principles through production, designing the systems that help AI agents reason, plan, and evaluate themselves. The work is high-autonomy and high-impact, sitting at the intersection of research and engineering.

What You'll Do

• Design and iterate multi-agent architectures that automate real accounting workflows, including autonomy boundaries, tool usage, and fallback behaviors.

• Manage context and memory for coherence across agent steps, and plan and execute agent loops with measurable success criteria.

• Route, evaluate, and optimize models under real-world constraints such as latency, cost, and accuracy.

• Build scalable evaluation pipelines (offline and online) that run experiments automatically, defining golden tasks, labeling strategies, and metrics.

• Instrument the stack to detect regressions, track error taxonomies, and drive closed-loop improvement.

• Architect prompt stacks and instruction hierarchies that structure model reasoning.

• Build retrieval and indexing pipelines that surface relevant context efficiently, and parse messy documents into structured representations.

• Design guardrails and validation layers to keep agent behavior safe and deterministic.

• Scope projects with clear specs and architecture docs, then build, test, and instrument systems end-to-end.

What We're Looking For

• 2 or more years of substantive ML engineering experience at a fast-paced startup, top-tier tech company, AI-native company, or hedge fund.

• Demonstrated experience building end-to-end LLM-based AI agent applications, including model orchestration, benchmarking, and evaluation frameworks.

• Deep expertise in Python and transformer-based systems.

• Experience running structured ML experiments: framing hypotheses, building evaluation infrastructure, and iterating on measurable results.

• Hands-on experience with agent systems and evals, rather than primarily classical ML.

• Strong fundamentals in machine learning from a technical degree (CS, Physics, Math, or similar) at a rigorous institution.

• Comfortable working fully on-site five days a week in a fast-paced startup environment.

• Currently based in the US or Canada; New York or East Coast preferred.

• Background in accounting, finance, or economics is a plus.

Compensation & Benefits

Base salary: $175,000 to $350,000 USD annually. Equity included. Visa sponsorship is available.

Location

On-site, five days a week in New York, NY, United States.