Engineering Tech Lead

Our requirements

• Strong proficiency in Java (Spring Boot): REST APIs, asynchronous/event-driven services, security, and performance tuning.
• Advanced front-end development experience with React, API integration, and modern UI patterns.
• Database expertise: PostgreSQL and in-memory databases (Redis).
• Experience with streaming/messaging platforms, preferably Kafka.
• Proven hands-on experience with production LLM applications, beyond prototypes or PoCs.
• Deep understanding of tokenization, context windows, temperature adjustments, and model limitations across major LLM providers.
• Strong capability in designing structured prompts for function/tool calling, generating structured JSON, and handling multi-turn conversations.
• Kubernetes (deployments, services, RBAC, Helm/Kustomize), autoscaling and observability principles.
• CI/CD (GitHub Actions, GitLab, Jenkins), IaC with Terraform.
• Cloud Infrastructure: AWS or GCP experience essential.
• Familiarity with LangChain, OpenAI/Azure OpenAI, Anthropic, or comparable LLM ecosystems.
• Understanding of model benchmark testing and risk classification in AI workflows.
• Knowledge of secure API/LLM gateway design.

Your responsibilities

• Design, build, and deliver production-quality services, ensuring compliance with enterprise controls and security standards.
• Enhance and optimise DecOps pipelines, improving CI/CD automation, testing frameworks, and system observability.
• Architect and maintain robust systems for high traffic and fault tolerance, optimising global resource allocation.
• Design and iterate on prompts for a broad set of LLM tasks: instruction-following, structured outputs, summarisation, reasoning, classification, and code generation.
• Manage prompt libraries with version control strategies, treating prompts as first-class engineering artefacts.
• Implement evaluation pipelines for prompt performance using tools such as PromptFlow, LangSmith, or custom frameworks.
• Architect and implement autonomous agent systems, multi-agent workflows, tool calling orchestration, and planning loops with memory-augmented reasoning.
• Integrate LLM observability capabilities—logging, tracing, evaluation, and automated guardrails—to ensure quality in production environments.
• Advise on Responsible AI deployment practices, including output validation, human-in-the-loop strategies, and risk mitigation for agentic workflows.
• Build and optimise Kubernetes deployments (Helm, Kustomize), implement HPA, RBAC and service ingress for secure and scalable operations.
• Maintain and improve CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins) for efficient and reliable delivery.
• Apply Infrastructure as Code (IaC) methodologies with Terraform, deploying across AWS or GCP environments.
• Note: Detailed project information will be shared during the recruitment process.

About the project

This is how we work on a project

• Continuous Deployment
• Continuous Integration
• documentation
• issue tracking tools
• testing environments

What we offer

• Flexible cooperation model – choose the form that suits you best (B2B, employment contract, etc.)
• Hybrid work setup – 1 day from the office per week
• Collaborative team culture – work alongside experienced professionals eager to share knowledge
• Continuous development – access to training platforms and growth opportunities
• Comprehensive benefits – including Interpolska Health Care, Multisport card, Warta Insurance, and more
• High quality equipment – laptop and essential software provided

Benefits

• sharing the costs of sports activities
• private medical care
• sharing the costs of professional training & courses
• life insurance

Mindbox Sp. z o.o.