All open roles

AI Solutions Engineer

  • Engineering
  • London, United Kingdom
  • Full Time
01Overview

About the role

Be the technical lead in front of Quillstone's banking and PSP customers for our LLM products in disputes, KYC and reconciliation. You will run discovery, build proofs of concept on customer data, design the solution and hand over something their engineers can run, and explain model limits clearly to risk committees.

Benefits & perks

  • Health Insurance

    Private medical insurance (Bupa) for you and dependants.

  • Equity

    Meaningful stock options, 4-year vest with 1-year cliff.

  • Flexible Work

    Hybrid: 2 days a week in the Shoreditch office.

  • Paid Time Off

    30 days holiday plus bank holidays.

  • Parental Leave

    26 weeks fully paid parental leave.

  • Wellness / Stipend

    £100 monthly wellness stipend.

02Responsibilities
  • 01Lead technical discovery with bank and PSP operations and engineering teams.
  • 02Build proofs of concept on customer data using our LLM and retrieval stack.
  • 03Write solution designs and support customer model-risk reviews.
  • 04Create evaluation sets that become customer acceptance tests.
  • 05Bring customer requirements back to the product and platform teams.
03Skills & competencies

What we evaluate against.

Applied Technical Depth

Must have

  • Has built an LLM-based proof of concept or product feature on real customer data.

Nice to have

  • Comfortable with structured outputs and tool calling.

Problem Decomposition

Must have

  • Has converted a vague customer ask into a scoped POC with acceptance criteria.

Nice to have

  • Writes solution design documents.

Customer & Domain Discovery

Must have

  • Has shadowed operational users and changed the solution as a result.

Nice to have

  • Payments, banking or disputes domain experience.

Product & Solution Judgment

Must have

  • Has scoped out or down an automation because of reliability or regulatory risk.
  • Has explained model limitations to a risk or compliance audience.

Nice to have

  • Built an evaluation set used as an acceptance test.

Execution Under Ambiguity

Must have

  • Has taken a customer from discovery to pilot or production.

Nice to have

  • Handled multiple concurrent customer engagements.
04Team dynamics

Team Structure

AI platform squad of 8 engineers working alongside disputes and reconciliation product teams.

Operating Rhythm

Two-week sprints, weekly customer calls, monthly model-risk review.

Communication

Written-first; design docs precede every customer POC.

Conflict Resolution

Disagreements settled on evaluation data, escalated to the CTO only on regulatory risk.

05Company culture

Ownership

Squads own their product metrics and their on-call.

Innovation

A tenth of every sprint is reserved for experiments.

Feedback

Written feedback cycles every six weeks.

Diversity & Inclusion

Structured interviews and published salary bands.

06What success looks like

First 30 days

Shadow two live customer engagements and ship a POC improvement.

90 days

Take that customer through model-risk review to a signed pilot.

Outcomes

Be the go-to engineer for our largest banking accounts.