Senior AI Agent Engineer: Production-Grade Agent Systems

EPAM Systems; Turkey; On-site; TRY 4,936,000 - 7,404,000; Full time

Benefits offered by this job

Continuous upskilling

Private health insurance

USD-based compensation

Learning platform access

Mentoring programs

Job summary

EPAM Systems is hiring to design and deliver AI agent systems that stay reliable beyond demonstrations. You will own technical decisions and delivery for a defined system, combining software engineering with practical agent development from requirements through production operation.

You will work with customers to turn needs into measurable acceptance criteria, build prototypes, and deploy production slices using cloud AI hosting services.

Qualifications

• Substantial production software engineering experience, typically five or more years, including at least one year delivering LLM‑based agents to production.
• Strong programming skills in at least one general‑purpose language with hands‑on agent development using SDKs or model APIs.
• Depth in at least one technical area and ability to evaluate trade‑offs against requirements.

Responsibilities

• Design, build, deploy, and operate agent systems across execution, memory, identity, tool integration, and observability.
• Translate needs into functional requirements and measurable acceptance criteria; prototype and production‑grade slices from design through deployment.
• Develop agent workflows and production deployments using cloud managed services for AI hosting (Bedrock, Azure AI Foundry, Vertex AI).
• Implement and operate an LLM gateway & routing layer with model tiering, quota/cost control, and observability.
• Design memory and context management for multi‑step workflows, including state persistence and isolation between users.
• Build and maintain MCP servers and tool integrations for secure workflows, defining contracts, permissions, and recovery behavior.
• Establish automated tests and agent evaluations; distinguish model quality issues from software defects.
• Diagnose production issues using logs, metrics, and traces; improve reliability, latency, and cost.
• Contribute to CI/CD, release checks, rollback plans, code reviews, and technical documentation; mentor others.

Skills

Production software eng

LLM-based agents

General-purpose language

SDKs/frameworks

English proficiency

Education

Bachelor’s degree in CS or related

Tools

Bedrock

Azure AI Foundry

Vertex AI

APIM AI Gateway

Job description

EPAM Systems is hiring to design and deliver AI agent systems that stay reliable beyond demonstrations. You will own technical decisions and delivery for a defined system, combining software engineering with practical agent development from requirements through production operation.

You will work with customers to turn needs into measurable acceptance criteria, build prototypes, and deploy production slices using cloud AI hosting services.