Applied Senior Software Engineer (AI Native Development)
Summary
Build and orchestrate AI agents that automate coding, refactoring and documentation for large codebases, integrating AI into CI/CD and engineering workflows.
EPAM Systems is a global team of technologists who design, develop and deliver software that powers the world. We are at a pivotal moment where AI is the core engine of our engineering craft. Join our AI‑Centric Delivery team as a Senior Software Engineer to redefine the Software Development Lifecycle (SDLC). Go beyond writing code to design and orchestrate AI agents and agentic workflows that accelerate development velocity. If you are a tool‑agnostic engineer focused on the future of AI‑native engineering, this role offers the opportunity to build, test and ship transformative technical solutions for global brands.
Responsibilities
- Design and build sophisticated AI developer agents capable of generation, refactoring and documentation of complex codebases at scale
- Champion the shift from manual coding to an agentic workforce while maintaining hands‑on technical involvement for high‑level precision
- Deliver functional, high‑velocity prototypes in tight windows to prove the real‑world power of AI‑driven engineering
- Design and integrate AI‑enabled workflows directly into the engineering stack, including Git, Jira and CI/CD pipelines, to automate processes and maximize developer throughput
- Consult with stakeholders to translate complex business requirements into AI‑SDLC‑augmented technical solutions
- Articulate the trade‑offs of agentic design and ensure alignment with enterprise goals
Requirements
- Extensive engineering background as a high‑performing developer with mastery of Java, JavaScript, Python or .NET
- Hands‑on expertise with large language models including Anthropic Claude, OpenAI GPT or Google Gemini
- Proven capability in development of agentic workflows that feature tool use, memory and multi‑step reasoning focused on engineering tasks
- Strong understanding of RAG architectures, prompt engineering and the mechanics of integration of AI into production‑grade SDLC workflows
- Execution‑focused mindset with a strong preference for construction, tests and shipment of working solutions
Nice to have
- Experience with multi‑agent orchestration frameworks like CrewAI or AutoGen
- Knowledge of vector databases such as FAISS, Pinecone, Qdrant or Chroma
- Familiarity with LLM evaluation, guardrails and observability
- Cloud deployment experience with AWS, Azure or GCP
- Practical experience with AI frameworks such as LangChain, Hugging Face or LlamaIndex