• Design and build the AI Agent Builder, a low-code tool for creating, testing, and deploying AI agents • Integrate LLM inference and agentic capabilities into gaiia's existing Workflow Engine • Build reusable AI components used by other squads across the platform • Evaluate and integrate new model capabilities, tool-use patterns, and orchestration frameworks • Contribute to architectural decisions around prompt design, evaluation, guardrails, and observability for production AI systems • Design, develop and deploy GraphQL APIs for both internal and external use • Develop intuitive interfaces for non-technical users to build and manage their own AI agents

Role Description Join PwC Slovakia as a Junior AI Engineer, where you'll have the opportunity to grow your skills and contribute to AI and data science solutions for leading global clients. This role is designed for developers and engineers who want to build, integrate, and deploy machine learning systems and data-driven applications. We are looking for candidates who enjoy coding in Python, working with data, and turning ideas into reliable, scalable solutions. - Projects you could be involved in: - Natural Language Data Exploration: Develop dashboards powered by AI for intuitive business data analysis. - Document Interaction: Design tools enabling seamless interaction with unstructured and structured text documents. - Knowledge Assistant: Implement ERP transformation with AI-powered tools to resolve employee inquiries efficiently. - Agricultural Monitoring: Utilize Computer Vision for analyzing satellite imagery on a large scale. - Automated Reconciliation: Create systems to identify anomalous transactions in accounting ledgers. - What You’ll Do: - Project Participation: Participate in AI and data science projects from conception to deployment, contributing to solution design and supporting timely delivery of assigned tasks. - Solution Development: Support the development of AI and ML solutions with a strong focus on Python-based implementation, working across areas such as Large Language Models (LLMs), RAG, classical machine learning and data analysis. - Learning & Development: Continuously develop technical skills by following AI and data science trends, learning new approaches, and contributing to improvements of existing solutions and processes. Qualifications - Solid programming skills in Python (e.g. pandas, numpy, scikit-learn, plotly). - Hands-on academic, project, or entry-level experience with machine learning, data science, NLP, Computer Vision, or Generative AI (LLMs, RAG). - Basic experience with SQL databases; familiarity with NoSQL databases is an advantage. - Strong analytical mindset with the ability to approach problems logically and creatively. - Ability to work independently on assigned tasks and deliver results with guidance when needed. - Fluent in English (B2 level or higher). Requirements - Ability to write and understand code is essential. - Experience with other programming languages is a plus. - Strong foundations in statistics and ML fundamentals are valued. Benefits - Work format: Remote or in a comfortable office in Lviv - you choose. - Development: Personal development plan, mentoring, English and Polish language courses. - Stability: Official employment from day one, annual review of salary and career prospects. - Corporate culture: Events that unite the team and a space where everyone can be themselves.

Role Description - Design and implement evaluation frameworks (evals) to assess LLM and agentic AI system quality, including accuracy, consistency, safety, and task completion rates. - Build and maintain automated test pipelines for AI features, covering unit, integration, and end-to-end scenarios across agentic workflows. - Develop tooling to detect regressions in model behavior, prompt outputs, and agent decision-making across releases. - Define and track quality metrics for AI systems (e.g., hallucination rates, tool-use accuracy, latency, failure recovery) and surface findings clearly to stakeholders. - Collaborate with engineers and product managers to identify edge cases, adversarial inputs, and failure modes specific to multi-step agentic pipelines. - Contribute to prompt evaluation strategies, including red-teaming, adversarial testing, and bias/fairness assessments. - Participate in design and code reviews with a quality-focused lens, raising concerns about testability and reliability early. - Help define and document quality standards and best practices for AI/ML features across the team. - Other duties as assigned. Qualifications - Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience. - 3–5 years of professional software engineering or quality engineering experience. - Hands-on experience working with LLMs or agentic AI systems (e.g., GPT-4, Claude, Gemini, or open-source models). - Proficiency in Python for scripting, test automation, and data analysis. - Experience designing and running evaluations (evals) for generative AI or LLM-powered features. - Solid understanding of software testing principles: unit, integration, regression, and end-to-end testing. - Familiarity with agentic frameworks and concepts (e.g., tool use, multi-step reasoning, retrieval-augmented generation, memory). - Experience with CI/CD pipelines and integrating automated tests into development workflows. - Strong analytical skills — able to interpret probabilistic outputs and distinguish meaningful regressions from expected variance. - Strong written and verbal communication skills; ability to clearly document findings and present quality data to non-technical stakeholders. - Detail-oriented, with a structured approach to exploring edge cases and failure scenarios. - Ability to work in a fast-paced environment and manage multiple priorities effectively. Requirements - Experience with prompt engineering and systematic prompt evaluation methodologies. - Familiarity with AI safety, alignment, or responsible AI concepts (e.g., hallucination mitigation, bias detection, guardrails). - Exposure to agentic orchestration frameworks (e.g., LangChain, LangGraph, AutoGen, CrewAI, or similar). - Experience with vector databases or RAG pipelines (e.g., Pinecone, Weaviate, pgvector). - Knowledge of observability and monitoring tools for AI systems (e.g., LangSmith, Weights & Biases, Arize). - Background in data science or ML experimentation practices. - Experience with version control systems (Git) and defect-tracking tools (e.g., Jira). - Exposure to cloud platforms (e.g., AWS, Azure, GCP) in the context of deploying or testing AI services. Benefits - Medical, Dental & Vision Benefits - 401(k) Savings Plan with Company Match - Flexible Planned Paid Time Off - Generous Sick Leave - Inclusive & Welcoming Environment - Purpose-Driven Culture - Work-Life Balance - Commitment to Community Involvement - Employer-Paid Parental Leave - Employer-Paid Short-Term Disability - Remote Work Flexibility

• Design and deploy production-ready AI agents that solve real business problems across ACQ Vantage • Build end-to-end agentic workflows, including tool use, memory, orchestration, and system integrations • Write and maintain high-quality code in Python and TypeScript for AI-driven applications and services • Integrate LLMs into internal systems, APIs, and data sources with a focus on reliability and performance • Evaluate, test, and improve agent behavior through prompt iteration, tool design, and structured evaluation • Collaborate with product and engineering teams to prioritize, ship, and iterate on AI features quickly