Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Datasnipper

NewBe an early applicant

Engineering Manager (Evidence Request Management)

Posted Updated

Description

  • We are hiring an Engineering Manager in our New York office to lead the Evidence Request Management team behind Alwin, our Agentic Automation Platform for audit and finance
  • Every audit starts with evidence, and getting it from the client is one of the slowest, most frustrating parts of the job: spreadsheets of requests, endless email chasing, and documents that turn out to be the wrong ones
  • Your team replaces that with agentic PBC (“prepared by client”): agents that draft requests from the audit plan, check every document that arrives against what was asked and the standards it must meet, and talk to the client directly to fix what is wrong
  • Pages missing from a bank statement, last year’s contract instead of this year’s, a sample that does not match the selection: the agent spots it, explains it to the client, and gets the right document, so auditors only see evidence that is ready to use
  • These agents run for days or weeks, act on behalf of the firm towards people outside it, and must know when to act alone and when to ask a human. Getting that right, at the scale of the world’s largest audit firms and their clients, is the job
  • Your team owns the evidence lifecycle, from first request to confirmed evidence
  • Plan & request: generating the request list from the audit plan, risk assessment and prior-year requests; assigning owners and deadlines on both sides
  • Validate against standards: automatically checking each document against the request and the applicable audit standards and firm requirements: right period, right entity, complete pages, matching samples, sufficient and appropriate evidence
  • Converse with the client: agents that explain exactly what is wrong or missing, answer clarifying questions, and follow up until the right document arrives, in a tone the firm would be proud of and without spamming anyone
  • Hand off: routing confirmed evidence into tasks, the workbench and downstream agent runs, with a full trail of who asked for what, and when
  • Client experience: the portal, notifications and permissions for external users, who are not our customers but decide whether this works
  • Lead through outcomes, not tasks. Set clear goals and trust the team to find the how
  • Build the team. Hire, grow and retain senior engineers in New York, and make the team measurably better every quarter
  • Own the technical direction of Evidence Request Management end-to-end, and stay close enough to the code to make the hard calls credibly
  • Make the agent a trusted voice to the client. Build conversational agents that represent the firm professionally, resolve issues in plain language, and know when a question needs an auditor instead
  • Turn standards into checks. Work with audit experts to encode what “good evidence” means for each request type, and measure how often the agent catches what an experienced auditor would
  • Design autonomy deliberately. Decide what agents may do on their own, what needs an auditor’s approval, and how every action they take towards a client is traceable
  • Build long-running systems that hold up. Event-driven agents and workflow state that survive partial deliveries, re-requests, deadline changes and rollovers between engagement periods
  • Win both sides of the table. Measure cycle time, chase volume and first-time-right evidence, and make the client side as good as the firm side
  • Work across Alwin. Partner with Agent Runtime, Document Intelligence, Evals, Product, Design and audit experts, many of them in Amsterdam, to deliver one coherent platform
  • Set the bar for AI-assisted engineering. Not just shipping faster, but taking on harder problems, and shaping how DataSnipper engineering uses AI
  • Hands-on experience with agentic or LLM systems in production: you understand control loops, tool calling, human-in-the-loop and evaluation well enough to challenge your team’s designs
  • An empowerment style of leadership and a track record of hiring and building high-performing teams
  • Experience building workflow-heavy products with multi-step state, notifications and permissions, ideally with users outside the customer’s own organisation
  • Hands-on fluency with AI coding tools and agentic harnesses, and a team that is measurably better for using them
  • Comfortable leading across time zones and offices, with clear written communication
  • 3+ years leading engineering teams, on top of 5+ years as a software engineer
  • Strong fundamentals in software architecture, distributed systems, APIs and cloud-native development
  • Strong product aptitude: you challenge framing, make roadmap trade-offs, and care about whether customers succeed with what you ship
  • Durable workflow engines (e.g. Temporal) or long-running, event-driven systems in production
  • Document processing: OCR, classification, structured extraction and their quality metrics
  • Conversational AI with external users: support agents, customer-facing assistants or similar, including tone, safety and escalation
  • Agent evaluation in practice: datasets, offline and online experiments, failure classification
  • Case-management, ticketing or client-portal products, and email, file-sharing or ERP integrations
  • Experience in regulated domains (audit, financial services, healthcare or similar), where traceability, approvals and access control are requirements
  • Governance at scale: permissions, approvals and data access across many enterprise customers and their clients
  • Working closely with Forward Deployed Engineers, Solution Architects and GTM teams, turning what they learn on enterprise rollouts into platform capabilities rather than one-offs
  • Domain experience in audit (PBC, engagement operations), accounting or fintech
  • Python, Azure and observability tooling
  • Recruitment Screen (30 minutes, online)
  • Hiring Manager Interview (30 minutes, online)
  • System design interview (60 minutes, online)
  • Product Insight Discussion (60 minutes, on-site)
  • Final Interview (30 minutes, online)

Skills

Apply

See also

Software Engineering jobs by country — openings, pay and top skills →