AI Infrastructure Engineer

We've been building digital products for over 10 years, with a strong focus on Blockchain-based applications. At 4soft, people come first - it's our team of passionate technologists that enables us to work with international clients and deliver innovative solutions. We believe in transparency, effective teamwork, and achieving real business outcomes for those we serve.

Want to work on AI infrastructure that powers cutting-edge crypto compliance products? Growth and a great team culture matter to you? 4soft is the perfect place to find both.

Join our client's brand-new AI Platform team and help shape the foundational infrastructure behind their next generation of AI-powered products.

Tech stack: AWS, Kubernetes, LangChain, LangSmith, Databricks, AgentBricks

As an AI Infrastructure Engineer, you will be responsible for:

• Building and maintaining core components of an AI platform: model serving infrastructure, prompt pipelines, evaluation suites, and integration patterns that enable product teams to use AI reliably and at scale.

• Supporting the development of agentic workflows, including tool use, orchestration scaffolding, and reliability mechanisms, as the company moves toward more autonomous AI capabilities in its products.

• Instrumenting AI systems for observability: tracking model calls, monitoring token costs, surfacing latency and quality signals, and co-building dashboards and alerts that keep production AI systems healthy.

• Designing and maintaining tooling and frameworks that govern how prompts are written, versioned, and tested across the organization, raising the baseline quality of AI interactions across all teams.

• Collaborating closely with engineers in domain teams to understand their AI integration needs and help them build on the platform's foundations - not around them.

• Keeping up with the fast-moving AI landscape: new model capabilities, emerging orchestration patterns, and evaluation techniques

What we expect from you:

• Practical experience building with LLMs or ML systems

• Familiarity with AI protocols (MCP, A2A, ACP) and genuine enthusiasm for keeping up with new trends in the industry.

• Solid software engineering fundamentals: you write clean, testable code, think about maintainability, and understand what it means to build something that will be operated in production.

• Deep understanding of context windows and their importance in extracting maximum value from agentic workflows (context rot, compaction, etc.).

• Experience in at least one of the following: API integration and orchestration, data pipeline development, model evaluation or testing, observability and monitoring tooling.

• A learning mindset, visible in how you talk about your work: what you've picked up recently, what you're still figuring out, and what drew you to AI engineering in the first place.

• English proficiency at C1 level or above (for international client collaboration).

• Polish language skills at B2 level or above (for smooth communication with the team).

Great if you also bring:

• Practical experience with tools from the LLM/agent ecosystem - LangChain, LangSmith, Databricks AgentBricks, or anything comparable.

• A background in prompt engineering, building eval datasets, or systematically assessing the quality of LLM outputs.

• Genuine interest in crypto and digital assets

• Exposure to regulated or compliance-sensitive environments, or first-hand experience with why auditability and explainability aren't optional when AI has real consequences.

• Familiarity with ML lifecycle tooling such as MLflow or Databricks ML.

What helps us stay balanced:

• Grow your skills and hobbies with us - make use of a dedicated training and wellbeing budget

• Work from home or the office - your choice, up to 100% remote

• Access to specialists whenever you need them via our LuxMed healthcare package

• If the gym is your second home, activate a Multisport card with us

• Looking for a long-term home? You're in the right place - stable collaboration, no dress code, no heavy atmosphere

• Our team knows how to have fun: board games, city outings, go-kart races, laser tag, great food on team retreats - we take integration seriously (in the best way :)