IDC's Data Engineering is seeking an Engineer, AI/NLP Engineering to design, build, and productionize agentic AI workflows that automate and scale IDC's data operations and analytics products. This role sits at the center of IDC's shift from static data pipelines to autonomous, tool-using AI agents multi-step systems that plan, call tools, retrieve and reason over IDC's proprietary data assets, and operate under human-reviewed guardrails in production.
You will build agent loops with tool calling, orchestration, and memory/state management, design evaluation harnesses that measure agent accuracy, latency, and cost; and implement retrieval-augmented generation (RAG) against IDC's intelligence assets so agent outputs stay grounded in verified data. This is a hands-on technical role for someone who has actually shipped agentic AI systems to production, not just experimented with them.
What You’ll Do
Operate extensively within Claude Code and other governed, AI-powered development workflows, applying guardrails such as safe-zone scoping and critically reviewing agent-generated plans.
Build and operate natural language processing (NLP) pipelines at scale that ingest, parse, chunk, embed, and extract metadata/entities from millions of documents, and extract insights via Large Language Models (LLMs) or NLP models.
Ramp quickly on unfamiliar codebases using documentation and skills files as the primary source of context.
Apply strong applied Python, SQL, and Snowflake fundamentals to assess solution feasibility and challenge technical proposals.
Manage stakeholder relationships and negotiations, securing specialist sign-off and communicating trade-offs or interim delivery options.
Exercise sound technical judgment, escalating and pushing back on unrealistic scope or timelines rather than overpromising.
What You Bring
Bachelor's degree in Computer Science, Data Science, Engineering, or a related quantitative field.
2+ years of experience in data science or AI/ML engineering, including at least 2 years hands-on building and shipping agentic AI or LLM applications in production.
Hands-on experience with machine learning, agent orchestration framework Claude Code/Claude Agent SDK and tool-calling / MCP-based integration patterns.
Strong applied Python, SQL, and Snowflake fundamentals enough to assess solution feasibility and challenge technical proposals.
Experience designing evaluation frameworks for agent accuracy, latency, and cost efficiency.
Working understanding of agentic-system failure modes (hallucination, drift, prompt injection, cost runaway) and how to mitigate them through guardrails and human-in-the-loop review.
Collaborate with global technical and analyst teams to gather requirements.
Travel: minimal (up to 10%).
Work model: Hybrid (Czech Republic).
What We Offer
5 weeks of holidays + extra corporate days off
Full time, permanent position offered in hybrid model (Prague or Ostrava office, 2 - 3 days office)
Flexibility to work from home most of the week
Sick days
Certain flexibility to schedule your working hours
Cafeteria system (use points on Flexipasses, pension/life insurance, or Multisport card)
Meal allowance
Compensation Transparency
At IDC, we are committed to fair and equitable pay practices. Employees are compensated equitably for their work, aligned with their skills and experience. Salary and incentive structures are determined through a rigorous process that considers experience, education, certifications, role-specific requirements, internal equity, and verified U.S. market data from an independent third-party partner.
Equal Opportunity Employer
IDC is committed to providing equal employment opportunities for all qualified persons. Employment eligibility verification required. We participate in E-Verify.
... (Snowflake or similar) and an orchestrator (Airflow or similar) - You explain technical trade-offs clearly to non-technical colleagues - 3+ years of hands-on engineering in data, software or AI Nice To Have - dbt in production - Pydantic AI, Langfuse or similar AI tooling - TypeScript for simple front ends - n8n, Zapier or ...
... concrete data and model requirements - Present results and trade-offs clearly to technical and non-technical audiences O pozici / o projektu Původní popisek. Senior Data Scientist – LLM / Clinical NLP Full-time B2B | Remote Poland | US Healthcare Real-World Data Context We are an AI-native data and technology partner for private ...
... delivery, including solutions leveraging AI/ML as well as modern data engineering and analytics platforms. - Contribute to internal R&D by evaluating emerging AI tools, libraries, frameworks, and modern data technologies (e.g., cloud-native data platforms, data engineering tools), and translating insights into recommendations ...
... and implement machine learning models and algorithms for real-world problems. - Collaborate with data scientists and engineers to preprocess and analyze large datasets. - Deploy AI models into production environments and ensure scalability and performance. - Conduct research on the latest AI trends and technologies to improve ...
Odpovědnosti Původní popisek. - Act as the subject-matter specialist for AI-enabled Software Development and Software Quality Assurance, maintaining current knowledge of large language models, AI development tools, AI agents and emerging technologies. - Research and benchmark AI applications, tools, vendors and industry ...
... adoption, and can show the impact in numbers - 3+ years of hands-on engineering, in a product, startup, solutions or data team Nice To Have - Snowflake, dbt, Airflow - Pydantic AI, Langfuse or similar - TypeScript or Streamlit for quick internal front ends Why Join? - A mandate to find and build AI opportunities across ...
... applied AI/ML engineering experience. - Advanced Python skills and proficiency with ML/DL libraries (PyTorch, TensorFlow, HuggingFace). - Hands-on experience with Databricks and MosaicML for production AI workflows. - Knowledge of RAG/CAG pipelines and integration with vector databases (FAISS, Weaviate, Pinecone, or Milvus). ...
... Description : We are looking for a Data Engineer to design, develop, and support scalable data solutions in a cloud-based environment. The role focuses on AWS, data processing, cloud data platforms, and modern data engineering practices. Responsibilities: - Design, develop, and maintain scalable data pipelines and data solutions. ...
... connections, skills, tests and guardrails), several agents working in parallel, and the checks that prove the output is correct before a client ever sees it. Context engineering, meaning capturing a client's data model, metric definitions and business rules in a form agents can use, is as much a part of the job as building pipelines. ...
... Role We are looking for a versatile Data & Analytics Engineer to support the development of our data and analytics capabilities. The role combines analytics engineering, data integration and Python-based AI/ML development. The successful candidate will be responsible for building and maintaining analytical data models, developing ...
... to Have • Experience in one or more industries, such as financial services, energy, manufacturing, or telecommunications. • Experience working in regulated or data-sensitive environments. • Experience with unstructured data, text analytics, or NLP. • Understanding of explainability techniques such as SHAP or LIME. • Familiarity ...