Senior AI-Native Engineer

Description

We are looking for a Senior AI-Native Engineer to join our team at EPAM Systems in Poland. We're looking for someone who doesn't just use AI — but thinks in AI. This role is built for engineers who approach every problem with an AI-first mindset, design systems where intelligent agents are core building blocks, and naturally embed AI into every stage of the software development process. If you're driven by the challenge of building truly autonomous, reasoning systems and want to define what AI-native engineering looks like at enterprise scale — we'd love to talk. This position offers a hybrid work model — combining remote work with 3 days per week from one of our EPAM offices located in Kraków, Wrocław, or Gdańsk. This setup allows you to enjoy flexibility while staying connected with your team and benefiting from in-person collaboration. Responsibilities Architect and develop AI-native applications where intelligent agents and LLM-powered components serve as foundational building blocks Design and implement multi-agent systems capable of autonomous reasoning, planning, tool selection, and execution of complex workflows Integrate Large Language Models into production environments, ensuring reliability, observability, and graceful degradation Embed AI throughout the software development lifecycle — from AI-assisted design and code generation to intelligent testing, review, and deployment automation Develop orchestration layers that manage agent communication, shared memory, context windows, and task delegation Craft and iterate on prompt engineering strategies to drive consistent, high-quality model outputs across diverse use cases Evaluate and benchmark emerging AI models, frameworks, and agent platforms to inform technology decisions Design feedback loops, guardrails, and evaluation mechanisms to ensure AI system safety, accuracy, and alignment Collaborate with cross-functional teams — including product managers, data engineers, and platform architects — to deliver AI-driven solutions at scale Contribute to the creation of internal standards, reference architectures, and reusable patterns for AI-native development Mentor engineers across teams on agentic design patterns, LLM integration best practices, and AI-first thinking Continuously monitor the evolving AI landscape and translate emerging research into practical engineering approaches Requirements Minimum of 5 years of professional software engineering experience with a demonstrated focus on AI-powered systems Proven, hands-on experience in AI Agents development or LLM integration — building and shipping applications where large language models drive autonomous reasoning, content generation, or complex decision-making Experience with AI orchestration frameworks such as Spring AI or LangChain4J for structured development of agent-based applications Strong Prompt Engineering skills — including designing prompt templates, chains, and system instructions that produce reliable, context-aware model behavior in production settings Proficiency in Python for AI/ML prototyping, model interaction, scripting, and working within the broader AI development ecosystem Hands-on experience with AWS or GCP cloud platforms, particularly services supporting AI/ML workloads (e.g., Bedrock, SageMaker, Vertex AI, Lambda, Cloud Functions) Demonstrated practice of embedding AI into the SDLC — actively using AI-powered assistants, agents, or copilots to accelerate and enhance software development workflows Strong system design skills with the ability to architect solutions that combine traditional services with autonomous AI components Critical thinking and ability to assess model limitations, hallucination risks, and appropriate use cases for AI automation Excellent communication skills and ability to work effectively in international, cross-functional Agile teams Proficiency in English (B2+), both written and spoken Nice to have Experience designing and implementing Retrieval-Augmented Generation (RAG) pipelines to ground model responses in verified, domain-specific knowledge Familiarity with Vector Databases (e.g., Pinecone, Weaviate, pgvector, Chroma, Milvus) for semantic search, similarity matching, and embedding management Understanding of Model Context Protocol (MCP) for enabling standardized interaction between AI agents and external tools, APIs, or data sources Hands-on experience with Anthropic Claude Code or similar agentic developer tools for AI-native software engineering workflows Familiarity with Google Agent Development Kit (ADK) for building, testing, and deploying multi-agent systems with structured orchestration

Requirements

• Minimum of 5 years of professional software engineering experience with a demonstrated focus on AI-powered systems

• Proven, hands-on experience in AI Agents development or LLM integration — building and shipping applications where large language models drive autonomous reasoning, content generation, or complex decision-making

• Experience with AI orchestration frameworks such as Spring AI or LangChain4J for structured development of agent-based applications

• Strong Prompt Engineering skills — including designing prompt templates, chains, and system instructions that produce reliable, context-aware model behavior in production settings

• Proficiency in Python for AI/ML prototyping, model interaction, scripting, and working within the broader AI development ecosystem

• Hands-on experience with AWS or GCP cloud platforms, particularly services supporting AI/ML workloads (e.g., Bedrock, SageMaker, Vertex AI, Lambda, Cloud Functions)

• Demonstrated practice of embedding AI into the SDLC — actively using AI-powered assistants, agents, or copilots to accelerate and enhance software development workflows

• Strong system design skills with the ability to architect solutions that combine traditional services with autonomous AI components

• Critical thinking and ability to assess model limitations, hallucination risks, and appropriate use cases for AI automation

• Excellent communication skills and ability to work effectively in international, cross-functional Agile teams

• Proficiency in English (B2+), both written and spoken

Responsibilities

• Architect and develop AI-native applications where intelligent agents and LLM-powered components serve as foundational building blocks

• Design and implement multi-agent systems capable of autonomous reasoning, planning, tool selection, and execution of complex workflows

• Integrate Large Language Models into production environments, ensuring reliability, observability, and graceful degradation

• Embed AI throughout the software development lifecycle — from AI-assisted design and code generation to intelligent testing, review, and deployment automation

• Develop orchestration layers that manage agent communication, shared memory, context windows, and task delegation

• Craft and iterate on prompt engineering strategies to drive consistent, high-quality model outputs across diverse use cases

• Evaluate and benchmark emerging AI models, frameworks, and agent platforms to inform technology decisions

• Design feedback loops, guardrails, and evaluation mechanisms to ensure AI system safety, accuracy, and alignment

• Collaborate with cross-functional teams — including product managers, data engineers, and platform architects — to deliver AI-driven solutions at scale

• Contribute to the creation of internal standards, reference architectures, and reusable patterns for AI-native development

• Mentor engineers across teams on agentic design patterns, LLM integration best practices, and AI-first thinking

• Continuously monitor the evolving AI landscape and translate emerging research into practical engineering approaches

Seniority

• Senior

Nice to have

• Experience designing and implementing Retrieval-Augmented Generation (RAG) pipelines to ground model responses in verified, domain-specific knowledge

• Familiarity with Vector Databases (e.g., Pinecone, Weaviate, pgvector, Chroma, Milvus) for semantic search, similarity matching, and embedding management

• Understanding of Model Context Protocol (MCP) for enabling standardized interaction between AI agents and external tools, APIs, or data sources

• Hands-on experience with Anthropic Claude Code or similar agentic developer tools for AI-native software engineering workflows

• Familiarity with Google Agent Development Kit (ADK) for building, testing, and deploying multi-agent systems with structured orchestration