Role & responsibilities :

- Embed with a delivery team to understand the process, the exceptions, and where professional judgment is applied.

- Run technical discovery across systems, data access, controls, volumes, edge cases and success measures.

- Reuse before building. Adapt proven engines from across the firm, including automation and document intelligence built by existing practices, under platform standards.

- Increase automation and autonomy only on the basis of production evidence.

- Establish a baseline before deployment, measure results after, and report both.

- Support adoption: train operators, provide close support at go-live, and resolve issues until usage is stable.

Qualifications :

- Bachelor's degree in computer science, Engineering, Information Systems or a related field.

- 5+ years of software engineering experience, including 2+ years deploying LLM-based systems used by non-technical users.

- Strong Python, with enough full-stack range to build a usable operator interface without waiting for a front-end team.

- Cloud fundamentals on Azure or AWS, including compute, storage, networking, identity, containers and CI/CD.

- Strong systems integration and data skills: REST APIs, webhooks, authentication flows, ETL and SQL.

- Experience with retrieval and document processing over unstructured enterprise documents, including parsing, table and form extraction.

- Experience with workflow and agent design, including tool calling, structured outputs and deterministic fallbacks.

- Ability to work with operational teams that do not report to you and build support for process change.

- Comfort with incomplete documentation, inconsistent source data and evolving scope.

Good to have :

- Prior forward deployed, embedded delivery or internal product engineering experience.

- React or similar for lightweight operator interfaces.

- Experience with observability tooling for LLM applications.

- Relevant Microsoft Azure or AWS certifications.