Senior Software Engineer (Agent Builder, Alwin by DataSnipper)
Posted Updated
Summary
Builds the authoring experience for Alwin, DataSnipper's agentic audit-automation platform, turning audit methodology into governed, versioned AI agents. Day-to-day work spans Python (FastAPI, Pydantic, MongoDB) on Azure and React, with agent runtimes, evals, tracing, and security for regulated audit customers.
- We are looking for a Senior Software Engineer in our New York office to join the Agent Builder team behind Alwin, our Agentic Automation Platform for audit and finance. Alwin agents run multi-step audit procedures over client evidence and return finished workpapers with every number traced back to source. Humans plan, review and sign off
- Agent Builder is where firms encode their methodology into agents. Methodology and quality teams describe how a procedure should execute; you build the product that turns that into a governed, versioned agent their whole firm can run consistently, every time. The problems are largely open: there is no playbook for letting auditors author production agents in a regulated domain, so you will help write it
- This is a hands-on role in a team that moves fast and holds a high bar. Your work goes in front of hundreds of thousands of audit and finance professionals at the world’s largest firms
- Build the authoring experience that encodes a firm’s audit methodology into a configurable, multi-step agent
- Design the agent definition model: steps, tools, inputs, thresholds, planning behaviour and human-in-the-loop gates
- Choose the right abstraction for builders, so non-engineers get consistent agents without writing prompts from scratch
- Work with the Agent Runtime team so authored agents compile cleanly onto the base agent, tools and orchestration layer
- Own versioning, publishing and governance in the Agent Library: who may build, publish and run which agent
- Give builders a way to test and evaluate an agent before publishing, working with the Agent Runtime and Evals teams
- Instrument authored agents in production and use traces (Grafana, OpenTelemetry, MLflow) to find where definitions break down
- Implement security, access-control and audit-trail requirements expected by regulated customers, aligned with OWASP GenAI
- Own features end-to-end in our Python stack (FastAPI, Pydantic, MongoDB) on Azure, through to the React web app
- Architect services with clear contracts that other Alwin teams can build on
- Raise the engineering bar through code reviews, mentorship and well-documented technical decisions
- Break down epics and manage ambiguity with product, design and audit methodology experts
- Experience with testing strategies (unit, integration, E2E) and a quality-first mindset
- Solid experience building data-driven web APIs on a major cloud platform
- A track record of owning product features end-to-end, including frontend work in React or a similar framework
- Proficient with AI-assisted engineering (we use Claude Code)
- Strong fundamentals in software architecture, system design and data modelling
- Experience with LLM APIs and agent frameworks across more than one model provider
- 6+ years in software engineering, with strong, production-grade Python
- Hands-on experience building and operating agentic systems in production: control loops, tool calling, planning versus execution, retries and fallbacks, not only prompt-and-parse pipelines
- Excellent communication; you can work directly with auditors and product partners to define what “correct” means
- Domain experience in audit methodology, accounting or fintech
- Experience with agent evaluation: datasets, offline and online experiments, failure classification
- Durable workflow engines (e.g. Temporal) or multi-agent orchestration in production
- Document processing: OCR, classification, structured extraction
- Experience with versioning, permissions and publishing in a multi-tenant platform
- Judgment: You exercise sound judgment in ambiguous situations, balance speed and accuracy, and adjust priorities proactively
- Experience building low-code / configuration products, workflow designers, rule engines or DSLs
- Ownership: You own work end-to-end, anticipate issues, and ensure high-quality delivery without close supervision. We expect you to influence the technical direction of the team
- Collaboration: You build strong cross-functional relationships and influence peers through expertise, data, and empathy
- Adaptability: You navigate ambiguity calmly, model positive behavior, and help peers adjust through clear communication
- Growth Mindset: You encourage open feedback exchange and provide clear, balanced feedback that helps others grow