Enterprise AI Architect
Bonapolia · Warszawa, PL ·
- Category
- Architecture
Bonapolia · Warszawa, PL ·
Paysend · Beograd, RS
IFS · London, England, gb
Starburst · United States
abstra
Hands-on Enterprise AI Architect who shapes and builds reusable LLM/agent-based AI skills for an enterprise client, owns the platform architecture and standards, and leads two AI Solutions Engineers, with a strong consulting and presales component. Core tech: LLM agents (tool use, MCP, prompt engineering), TypeScript/Node.js or Python/Java/.NET, CI/CD.
About the role
We are looking for an Enterprise AI Architect to own the technical shape of an enterprise AI capability for our client. You will work directly with senior business stakeholders, decide what is worth automating, design and build reusable AI skills, and lead a small team of two Lead AI Solutions Engineers. This is a hands-on architecture role with a strong consulting and presales component.
What you will do
Shape the work
Work with senior business stakeholders and domain experts to define objectives, constraints and expected outcomes
Identify which processes are worth automating and which are not, and say so when the answer is no
Select tools, platforms and approaches for each business problem and defend the choice to both technical and business leadership
Shape and present solution proposals: scope, approach, effort, expected impact
Own outcomes with a product mindset: adoption, measurable time saved, reliability for real users
Own the architecture
Own the technical shape of the whole capability: standards, shared components, evaluation and release strategy, backwards compatibility
Define what a well-formed skill looks like, what belongs in shared infrastructure and what gets rejected in review
Make and justify platform-level decisions: agent harnesses, integration architecture, build vs adopt
Apply sound judgement on data handling, security and compliance when working with sensitive HR and compensation data
Provide technical leadership to two engineers: review, direction, unblocking
Build it
Design, build, test and maintain reusable AI skills: instructions, scripts, validation logic, reference data, shared components
Write and review production-quality code and own it through review, CI and release
Build the evaluation layer: golden cases, acceptance criteria, regression checks
Debug agent behaviour and fix root causes
Integrate with the client’s platforms and data sources
Drive it forward
Run pilots with real users, collect structured feedback and ship improved versions
Set and enforce standards for authoring, reviewing, versioning and releasing skills
Track where AI tooling is going and bring relevant parts into the engagement early
Must have
Architect-level experience with proven ownership of real systems: module boundaries, reuse, versioning, integration, non-functional requirements
Still hands-on: you write and review production code today
Strong engineering foundation in at least one modern stack (TypeScript / Node.js is a plus, Python, Java or .NET backgrounds are welcome)
Solid engineering practice: version control, code review, automated testing, CI/CD
Real LLM-backed systems shipped to real users, not just prototypes
Broad hands-on knowledge of the current AI tooling landscape, not tied to a single vendor
Working command of agentic patterns: tool use / function calling, MCP, prompt and context engineering, orchestration
Experience evaluating non-deterministic systems with test sets and measurable acceptance criteria
Judgement on where AI fits and where conventional software is the better answer
Direct experience with external clients and senior business stakeholders, including CTO-level conversations
Presales experience: shaping, scoping, estimating and pitching solutions
Ability to turn ambiguous requirements into a clear design and work without a full specification
English C1
Sustained working-hours overlap with US / Western Europe
Nice to have
Hands-on experience with Claude Code, especially authoring Skills, plugins or MCP servers
LLM evaluation tooling (promptfoo, LangSmith, custom harnesses)
Consulting or professional services background
Exposure to HR tech, compensation & benefits, payroll or workforce analytics
Experience building internal developer tooling or a platform capability
Public work: open-source agent tooling, published skills or plugins, talks, technical writing
📩 Ready to Join?
We look forward to receiving your application and welcoming you to our team!
Square One Resources · Poland