Инженер данных

EPAM provides digital platform engineering services, software product development, and digital solutions.

• Maintain, refactor, and extend the line's AI applications and services in production;
• Build agentic-friendly software: the tools, services, and workflows that LLM-based agents call;
• Design AI workflows that combine models, prompts, tools, enterprise data, and business logic;
• Validate model behavior, outputs, and assumptions from an engineering and production perspective;
• Design and maintain evaluation frameworks for AI/LLM systems, including test suites and human evaluation workflows;
• Write evaluations and quality checks for agent behavior, and build in grounding and assurance;
• Ensure reliability, scalability, cost control, and latency optimization;
• Help bring new agentic systems into production.

• 5+ Years of experience in strong software engineering, primarily in Python, with other modern languages (TypeScript, Java, Kotlin) acceptable where production-quality code delivery is demonstrated;
• Forward Deployed Engineer mindset, with a desire to understand the business problem and the impact of the solution, and drive pragmatic decisions toward realizing it, including API, service, and integration engineering;
• Proficiency in LLM application patterns (prompting, retrieval-augmented generation, tool/function calling) and proven agentic development practice;
• Expertise as a daily practitioner of agentic coding harnesses (e.g. Claude Code), including spec-first decomposition, directing agents to build and modify production code, and critically reviewing and owning generated output;
• Capability to pick up and improve an existing codebase;
• Skills in validating AI model behavior and outputs from an engineering and production standpoint, rather than a Data Science or ML research perspective;
• Hands-on experience in agentic/LLM application development, including agent loops, evaluations, and tool design;
• English proficiency at B2 level or higher;
• Nice to have: Familiarity with Palantir Foundry / AIP, Background in insurance or reinsurance domain, Familiarity with cloud AI services (e.g. Azure AI).

• No conditions specified