Senior AI Software Engineer (.NET)

Zenio; Województwo mazowieckie; On-site; PLN 180,000 - 240,000; Full time

Job summary

Zenio is building AI-powered production software, integrating LLMs and agent tooling into .NET services and Vue.js-based frontend components. You will help design the boundaries between logic and AI, implement robust validation, and ensure trustworthy AI with observability and guardrails.

You’ll own features end to end, from problem framing with product to deployment in production, while focusing on simplicity and explicit logic over magic abstractions.

Qualifications

• Ability to navigate uncertainty and work in ambiguity.
• Experience shipping AI features to production with reliable observability.

Responsibilities

• AI in production: build LLm- and agent-powered features into production .NET services.
• Design seams between deterministic logic and probabilistic AI with validation and human-in-the-loop.
• Own features end to end, from framing the problem to running in production.

Skills

.NET

AI in production

Structured outputs

Problem solving

Tools

.NET

Vue.js

Semantic Kernel

Vector search

Job description

Logistics operations today are still largely:

• manual
• reactive
• fragmented across tools
• running on incomplete or late data
• full of conflicting constraints
• driven by evolving business rules
• a mix of legacy and new systems

Much of this is unstructured: emails, documents, free-text updates, exceptions nobody modelled. That is where AI changes the game.

We’re building a system that:

• ingests real-time operational data, structured and unstructured
• supports planning and execution decisions, with AI agents that act where it’s safe and hand over to humans where it isn’t
• adapts to constantly changing constraints

What You’ll Work On

• AI in production. Building LLM- and agent-powered features into production .NET services: tool calling, structured outputs, retrieval over operational data, document and message understanding.
• The seams. Designing the boundaries between deterministic business logic and probabilistic AI: validation, fallbacks, human-in-the-loop.
• Trust. Making AI measurable and trustworthy: evals, test sets, observability, guardrails and cost/latency budgets.
• Ownership. Owning features end to end, from problem framing with product to running them in production.
• keep things simple before scalable
• prefer explicit logic over magic abstractions, and that includes AI: deterministic where you can, model where you must
• optimize for change, not perfection (models, prompts and providers will change)
• measure AI behaviour, don’t trust vibes
• accept that some parts will be ugly, temporarily

.NET · Vue.js · service-oriented architecture · relational + operational data storage · cloud-based infrastructure · LLM APIs and agent tooling (e.g. Semantic Kernel / Microsoft.Extensions.AI, MCP) · vector/semantic search · eval and tracing tools

How We Build

• AI-native development is the default. You use coding agents (e.g. Claude Code, Copilot) every day.
• You own what you ship, whoever typed it: you review AI-generated code critically, test it and understand it.

What We Expect

• Ability to navigate uncertainty and work in ambiguity
• Willingness to challenge decisions
• Focus on outcomes, not just code
• Understanding of trade-offs and complex systems, including when not to use AI
• Preferring ownership over comfort

Strong Plus

• Having shipped LLM/AI features to production and kept them running
• Experience with evals, prompt/version management or AI observability
• Python for prototyping and data work
• Logistics or other real-time operations domain experience

What You Won’t Find Here

• over-engineering everything upfront
• unnecessary microservices
• “clean architecture” for the sake of it
• AI demos that never reach production
• wrapping a chatbot around a problem and calling it solved