Senior Software Engineer – Evidence Agents (Alwin by DataSnipper)

DataSnipper•New York, NY

4d•$225,000 - $235,000•Hybrid

About The Position

DataSnipper is hiring a Senior Software Engineer for its Evidence Request Management team in New York. The team builds evidence-request agents for Alwin, DataSnipper’s agentic automation platform for audit and finance. These agents draft requests from audit plans, follow up with clients, review incoming evidence, and pass confirmed evidence to downstream workflows. The agents operate over days or weeks, respond to external events, and determine when they can act independently and when they should ask a human. This is a hands-on role building agent behavior, workflow state, and firm- and client-facing experiences. The engineer will own features end-to-end, contribute to production reliability and accuracy, and collaborate with product, design, audit domain experts, and other engineering teams. The role uses Python, FastAPI, Pydantic, MongoDB, Azure, and React, with production instrumentation including Grafana, OpenTelemetry, and MLflow.

Requirements

At least 6 years of software engineering experience, including strong, production-grade Python.
Hands-on experience building and operating agentic systems in production, including control loops, tool calling, retries and fallbacks, and human-in-the-loop workflows; experience limited to prompt-and-parse pipelines is not sufficient.
Experience building workflow-heavy products with multi-step state, notifications, and permissions, ideally involving users outside the organization.
Solid experience building data-driven web APIs on a major cloud platform.
Strong fundamentals in software architecture, system design, and data modelling.
Track record of owning product features end-to-end, including frontend work in React or a similar framework.
Experience with unit, integration, and end-to-end testing strategies and a quality-first mindset.
Proficiency with AI-assisted engineering; the team uses Claude Code.
Excellent communication skills and ability to work directly with auditors and product partners to define correctness.

Nice To Haves

Experience with durable workflow engines such as Temporal or long-running, event-driven background jobs.
Document-processing experience, including OCR, classification, structured extraction, and related metrics.
Experience with agent evaluation, including datasets, offline and online experiments, and failure classification.
Experience with case-management, ticketing, or client-portal products.
Experience with email, file-sharing, or ERP integrations.
Domain experience in audit (PBC or engagement operations), accounting, or fintech.

Responsibilities

Build agents that manage the evidence-request lifecycle, from drafting and assignment through follow-up, receipt, review, and closure.
Design long-running, event-driven agent behavior that responds to client uploads, replies, and deadlines over days or weeks.
Build agents that validate received evidence against requests, flag missing samples or incorrect documents, and decide when to escalate to a human.
Collaborate with the Agent Runtime and Document Intelligence teams on agent tools, extraction, and evaluation.
Model workflow state across firm and client users, including partial deliveries, re-requests, and rollovers between engagement periods.
Build firm- and client-facing experiences in React, including notifications, reminders, and permissions for external users.
Connect requests to the rest of Alwin so confirmed evidence flows into tasks, the workbench, and downstream agent runs.
Implement security, access-control, and audit-trail requirements for regulated customers and their clients, aligned with OWASP GenAI.
Own features end-to-end in the Python stack on Azure.
Instrument agents in production and use traces to improve reliability and accuracy.
Raise engineering standards through code reviews, mentorship, and well-documented technical decisions.
Break down epics and manage ambiguity in collaboration with product, design, and audit domain experts.