Member of Technical Staff - Applied ML

About the Role

This is an applied ML engineering role at a fast-growing fintech startup building agentic AI for accounting professionals. You will own end-to-end projects that bring intelligence into production, blending research-minded thinking with practical engineering to deliver safer, smarter agent workflows at scale.

What You'll Do

• Design and iterate multi-agent architectures that automate real accounting workflows end-to-end.

• Encode autonomy boundaries, tool usage, and fallback behaviors to keep agents safe and reliable.

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

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

• Design and implement 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 taxonomies, and drive closed-loop improvement.

• Architect prompt stacks and retrieval pipelines, and parse messy documents into structured representations for reasoning.

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

• Scope projects with concise specs, and communicate progress, learnings, and next steps within your pod.

What We're Looking For

• 3+ years of AI/ML engineering experience with strong computer science fundamentals; a background in math or physics is a plus.

• Hands-on experience designing and iterating multi-agent architectures and end-to-end LLM applications.

• Experience with benchmarking, model orchestration, and evaluation of agent behavior and reliability.

• Demonstrated ability to run structured ML experiments: framing hypotheses, building evaluation infrastructure, and iterating on measurable results.

• Experience building retrieval and indexing pipelines, and parsing unstructured documents into structured representations.

• Proficiency in Python and deep familiarity with LLM/transformer-based systems.

• Prior experience at a fast-paced startup (Series A-D), tier-1 tech company, AI-native company, or hedge fund.

• A technical undergraduate degree (CS, Physics, Math, or similar) from a strong academic program.

• Excited to work in-office full-time and thrive in a startup environment.

• Currently located in the US or Canada.

Compensation & Benefits

Salary range: $175,000 to $300,000 USD annually. Visa sponsorship is available.

Location

On-site, 5 days per week in New York, NY, United States.