Technical Lead, Senior AI Engineer - VonHalsky (m/f/n)

InPost UK; Kraków; On-site; PLN 320,000 - 420,000; Full time

Benefits offered by this job

Hybrid work from Warsaw or Kraków

Flexible hours

B2B contract

Training opportunities

Access to frontier models

Open-source track

Job summary

InPost Group, the team behind Von Halsky, seeks a Technical Lead, Senior AI Engineer to own the Evaluations Platform and guide the next phase of production-grade AI tooling. You will oversee the LLM-judge, curate eval datasets, and drive measurable improvements in conversation quality.

You will mentor engineers, define the technical direction, and collaborate with PM/EM to deliver impactful outcomes in a hybrid setup from Poland’s key cities.

Qualifications

• 5+ years building and running production software with 2+ years on LLM-based systems.
• Strong engineering fundamentals and production ownership habits (testing, CI/CD, containers, observability, cloud).
• Experience evaluating generative systems: LLM-as-judge, calibration, and regression suites.
• AI engineering fundamentals: prompt/context engineering, tool use, multi-turn state, and observability tooling.
• Data at scale: SQL and data lakes/warehouses with reproducible metrics.
• Fluent English (B2) and Polish for user-conversations and disclosures.

Responsibilities

• Own the LLM-judge pipeline and eval-driven development.
• Develop eval datasets and maintain a comprehensive golden set.
• Perform root-cause analysis on real conversations and improve diagnosis.
• Maintain the interface to product and business with measurable, actionable results.
• Mentor engineers and help define technical direction for the platform.

Skills

Production software

LLM systems

CI/CD

Python

Observability

Cloud

SQL

English B2

Polish

AI eval tooling

Tools

LangFuse

Braintrust

Weave

Claude Code

Cursor

Copilot

Job description

Technical Lead, Senior AI Engineer - VonHalsky (m/f/n)

• Contract

InPost Groupis an innovative European out of home deliveries company, revolutionizing the way parcels are delivered to customers. With operations across several countries, our network of intelligent lockers provides customers with a fast, convenient, and secure delivery option. InPost Group is a publicly traded company, with a market capitalization of about $5 billion as of March 2023. With over10,000 people worldwide, InPost Group is one of the largest out of home delivery providers in Europe, committed to providing sustainable and efficient delivery solutions to meet the evolving needs of customers in today's rapidly changing landscape.

We are a team that builds the best FMCG e-commerce in Poland.We already have over300,000 productsin our offer, we work with over300 sellers, and our mobile application has already been downloaded by almost1.5 million users in Poland. Due to the fact that our product consists of many elements that must work together efficiently and be managed effectively,we are looking for experienced consumer-focused (Web / Mobile App products) engineering leaders to join us in that journey- heavily influence our future platform build, improve processes and help us deliver best customer experience in the market across all types of devices.

Why this role exists

Von Halsky is InPost's conversational AI shopping assistant, live in production and serving a growing share of our customers. What decides whether it wins is not the model but whether we can tell, at release cadence, that a change made conversations better. That is the Evaluations Platform, and we are hiring the engineer who takes it to the next level.

What you will own

• The LLM-judge pipeline. Our release-gating judge over real and golden conversations, calibrated well enough that people act on its verdicts instead of arguing about it.
• Eval datasets and the golden set. Real coverage across intents and categories, including the Polish-language coverage generic benchmarks do not give us.
• Root-cause analysis on real conversations. Making our conversation-mining stack diagnostic rather than descriptive, on a stable issue taxonomy.
• The "sus" detector. Abusive, adversarial and anomalous sessions, next to our guardrails and red-team work.
• Evals-driven development. The eval comes before the feature, and writing it is as cheap as writing the code.
• The interface to product and business. Vague asks in, measurable quality definitions out, and results stakeholders can act on.

What "leadership aspirations" means here concretely

This is a technical lead role, not a people-management role, and you will not carry line-management duties on day one. You will set and defend the technical direction for the platform, act as reviewer of record for the area, mentor other engineers, scope work with our PM and EM, present results to stakeholders, and hold the line against ad-hoc requests crowding out platform work.

Engineering management later, or a Staff-level hands-on track, are both paths we will build with you. Either way we need someone accountable for an area rather than for a ticket.

How we define success in this role

• Judge pass rate is calibrated against human labels and is a number people trust and cite.
• A stable, versioned issue taxonomy is live and week-over-week trends are comparable.
• Every release is gated by an eval run the team can reproduce.
• The golden set has documented coverage and named blind spots.
• At least two engineers besides you can operate and extend the platform.

What we are looking for

Required

• 5+ years building and running production software, with 2+ years on LLM-based systems that real users hit.
• Strong engineering fundamentals, plus the habits that go with production ownership: testing, CI/CD, containers, observability, and working in cloud. We work primarily in Python.
• Demonstrable experience evaluating generative systems, not only building them: LLM-as-judge, human-label calibration, inter-annotator agreement, regression suites, offline-versus-online divergence. You should have opinions about what makes an eval worthless.
• AI engineering fundamentals. Prompt and context engineering as a discipline (context-window budgeting, structured outputs, failure-mode taxonomies); agentic primitives in production (tool use, multi-turn state, MCP, agent-to-agent integration patterns); and eval and LLM-observability tooling (LangFuse, Braintrust, Weave or equivalent, including things you built yourself).
• Comfort with data at scale: SQL, working with a lake or warehouse, and building a metric someone else can reproduce.
• Fluency with AI-assisted development tooling (Claude Code, Cursor, Copilot). We use it daily and expect it.
• Ability to make a technical argument to a non-technical audience and be understood.
• English B2 and Polish. Our users converse in Polish and you will read their conversations; judging quality you cannot read is not possible.

Nice to have

• Harness and loop engineering. Building the scaffolding around models rather than only calling them: agent loops, retries and fallbacks, tool-call orchestration, deterministic replay, and the plumbing that makes a non-deterministic system testable.
• Auto-improving systems. Closing the loop from production signal back into the product: mining failures into cases, using eval results to drive prompt, retrieval and routing changes, and automating the parts of that cycle that people do by hand today.
• Adversarial robustness, jailbreak testing, red-teaming, or abuse and fraud detection.
• E-commerce, search or recommendation domain experience.

What we offer

• A product that has already been released to millions of users, with a real business case, not a lab pilot.
• Direct access to frontier models at committed capacity across multiple providers, plus an open-source track we run ourselves.
• A quality mandate with executive attention.
• Ownership of a platform that is greenfield in practice inside a company with production traffic, which is the rarest combination in this market.
• Hybrid working from Warsaw or Kraków, in a team growing fast enough that early hires shape how it works.
• Fulfilling careers with arange of benefitsfor people and investing in providingtraining opportunitiesfor their development.
• You will feel a part of the InPost community that makes an impact on sustainability, convenient deliveries, and the circular economy every day.
• Excellent working environment and flexible hours
• We offer B2B type of contract