AI Product 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-powered tools that help compliance teams investigate crypto transactions faster and with greater confidence? Growth and a great team culture matter to you? 4soft is the perfect place to find both.

Tech environment: TypeScript, Node.js, LangChain, LangGraph, AWS, PostgreSQL, LLM frameworks
As an AI Product Engineer, you will be responsible for:
• Building and maintaining AI-powered features and agentic workflows using LLM frameworks such as LangChain and LangGraph, enabling compliance teams to make faster, more confident decisions
• Designing prompts, tool integrations, and retrieval pipelines that turn complex blockchain data into useful answers for investigators
• Ensuring the quality, reliability, and performance of AI systems - developing and running evaluations, and weighing trade-offs across cost, latency, and quality
• Strengthening pipeline reliability, observability, and automation through continuous improvements to code and tooling
• Designing and building the backend services, APIs, and event-driven systems that support these features, using TypeScript and Node.js
• Collaborating closely with product managers, domain experts, web engineers, and your engineering lead to take features from prototype through to production
• Keeping up with the fast-moving AI landscape: new frameworks, agentic patterns, and automation techniques - bringing relevant insights to the team

What we expect from you:
• +6 years of software engineering experience, with at least 1-2 years of meaningful production work building LLM-powered features
• Practical knowledge of LLM frameworks such as LangChain, LangGraph, LlamaIndex, or similar
• Practical understanding of prompt engineering, tool/function calling, subagents, structured outputs, and managing context windows
• Strong backend skills in TypeScript / Node.js, with solid API design.
• Experience evaluating LLM outputs and iterating on prompts/pipelines, including using observability tools (LangSmith, Langfuse, Arize, or similar)
• Familiarity with cloud infrastructure - AWS (Lambda, ECS, S3, or similar)
• Understanding of architectural trade-offs specific to LLM systems: cost vs latency vs quality, deterministic vs probabilistic behaviour
• 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:
• Experience with agentic patterns: planning, multi-step reasoning, tool use loops
• Hands-on work with Infrastructure as Code (Terraform or CloudFormation)
• Knowledge of container orchestration (Docker, Kubernetes, Helm)
• Experience working with multiple model providers (Anthropic, OpenAI, open-weight models)
• Experience with observability platforms like Datadog (metrics, tracing, alerting)
• Distributed or event-driven architectures (SNS, SQS, etc.)
• An interest in cryptocurrency, blockchain, or compliance, or a desire to learn

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 :)