Senior AI Engineer

Ataccama is the agentic data trust company. Organizations worldwide rely on Ataccama ONE, the agentic data trust platform, to ensure data is accurate, accessible, and trusted for every decision and system. Powered by the ONE AI Agent, Ataccama ONE brings autonomy to data quality and governance, continuously monitoring, improving, and explaining the reliability of data across complex enterprise and multi-agent environments. At the core of the platform is Ataccama’s market-leading data quality, with modules built around it to unify data quality monitoring, catalog, lineage, observability, and reference data management, ensuring data is consistent and explainable. This quality-first foundation makes data the engine of trust, powering AI, analytics, and operations with confidence. Recognized as a Leader in the 2026 Gartner Magic Quadrant for Augmented Data Quality and positioned furthest in Completeness of Vision , Ataccama continues to set the standard for enterprise-grade data trust. Our people are located across the globe. They succeed by collaborating as a team and thrive in our company culture defined by these core values: Challenging Fun ONE Team Customer Centric Candid and Caring Aim High Our AI team are the evangelists of Artificial Intelligence at Ataccama. We build the AI agents that power data quality, cataloging, and governance workflows across our platform — moving cutting-edge research into reliable, production-grade features our customers depend on. As a Senior AI Engineer , you'll own the design and reliability of the LLM agents at the heart of our AI-powered platform. This is a hands-on individual-contributor role for someone who has built agents that run in production — and knows what it takes to keep them fast, correct, and observable at scale. Your work will include: Designing, building, and hardening LLM agents with real tool use and multi-step orchestration for data quality, catalog, and governance tasks. Owning agent reliability end to end — latency, correctness, and cost — including evaluation harnesses and production observability. Designing and evolving our agent tooling layer, including MCP servers and protocol-level integrations, so capabilities can be exposed cleanly and securely. Building and tuning RAG pipelines and grounding strategies where agents need reliable access to customer data and metadata. Working across our LLM gateway (LiteLLM proxy) and model providers to route, monitor, and optimize inference. Setting technical standards for how we build agents, and raising the bar for the whole team through design reviews and pragmatic architectural trade-offs. What we're looking for Strong, modern Python and a track record of shipping LLM agents to production — not just prototypes or demos. Hands-on experience with agent architectures: tool calling, orchestration, and the failure modes that come with them. Practical experience with MCP (or comparable protocol/tooling design), and the judgment to know when a protocol layer is worth it. Experience building agent evaluation and observability — you measure quality and latency, you don't guess at them. Familiarity with RAG, retrieval, and grounding techniques and their real-world limitations. Comfort with LLM gateways/proxies (e.g. LiteLLM) and provider APIs (Azure AI Foundry, OpenAI, or similar). Healthy skepticism toward hype — you surface trade-offs before recommending a direction. Nice to have Kubernetes, AWS, or Azure experience. Background in data management, data quality, or governance. Exposure to OAuth2/SSO and multi-tenant service design. Perks & Benefits • Long-Term Incentive Program • 2 sick days and 25 days of vacation, with the option to request additional Flexible Time-Off days when needed • The Global Family Support Program - a paid leave program to help all parents focus on the new addition to their family • Flexible working hours & hybrid work setup • Benefit Plus - flexible employee benefit platform (incl. Multisport card) • Annual package for mental health support • "Bring Your Friend" referral program • Shared company cards for free entrance to Prague Zoo & Botanical garden • Company bikes, longboards, e-scooters • Conference tickets to the best industry events of the year • Online courses & company access to Udemy to hone your skills • Access to paid AI tools • Company library, where you can even suggest the best educational books for us to order • Kitchens stocked with fresh fruit and juice, teas, and the best coffee Work Equipment • Company laptop • Company mobile phone + SIM card & package of mobile data At Ataccama , our core values are Candid & Caring , so we are upfront about our process and details that are important to you. We sometimes use AI tools to help us with things like reviewing applications, taking notes from screening conversations, scheduling interviews, or supporting assessments. These tools make the process smoother and fairer — but don’t worry, they never make the final decision. Every hiring decision is made by our Talent Acquisition Partners and Hiring Managers, with AI only acting as a helpful assistant. We believe technology should support the process, not replace the human touch. We currently use AI-assisted tools - Metaview for interview notes and Lever Talent Fit to help highlight key experience. If you have any questions or concerns, feel free to reach out to us at [email protected], making reference to AI Act Inquiry in the subject line. While we highly value cooperation with all our business partners, we don’t accept unsolicited resumes from any sources other than directly from a candidate. We reserve the right not to pay any fee for sending an unsolicited offer containing the details or resume of a job candidate, even if the relevant candidate is employed by our company.