Lead AI Agent Engineer

EPAM Systems, Inc.; Turkey; On-site; TRY 1,000,000 - 1,500,000; Full time

Benefits offered by this job

Continuous upskilling

Diversity of tasks

Mentoring programs

English courses

Job summary

EPAM Systems, Inc. is seeking a hands-on senior technical leader to design and deliver production AI agent solutions.

You will steer architecture, engineering, and team delivery, work with customers to define requirements, and ensure technical quality and operational readiness across the work. The role values strong language proficiency and a capacity to learn new tools while guiding engineers through implementation.

Qualifications

• Substantial experience delivering and operating production software with a focus on AI agents.
• Demonstrated leadership and team delivery in shipping features and solutions.
• Experience designing system components and making trade-offs based on business needs.

Responsibilities

• Lead solution design across agent execution, memory, identity, tool integration, and observability.
• Personally build prototypes and production-grade slices through implementation, testing, and deployment.
• Guide production readiness, incident response, and observability while managing risks and technical debt.

Skills

LLM-based agent development

Distributed systems

Cloud platforms

Technical leadership

Prototyping & implementation

Tools

Bedrock

Vertex AI

Azure AI Foundry

MCP tooling

Job description

Lead the technical design and delivery of production AI agent solutions. This is a hands-on technical leadership role combining architecture, engineering, and team delivery. You will work with customers and stakeholders to define the right solution, guide engineers through implementation, and take responsibility for technical quality and operational readiness across the team's work.We welcome engineers from different programming backgrounds. We value depth in your existing language and the ability to learn the languages and tools needed for the role.ResponsibilitiesLead solution design across agent execution, memory, identity, tool integration, and observability Turn customer needs into clear requirements, compare alternatives, and explain the business and technical reasons for the chosen approachGuide the team's use of cloud managed services for AI hosting (e.g., Bedrock, Azure AI Foundry, Vertex AI) Establish implementation patterns and validate platform choices against reliability, security, cost, and operational requirementsDesign and guide implementation of an LLM gateway & routing layer covering model tiering, quota/cost control, and observability (e.g., LiteLLM, APIM AI Gateway)Design and review memory, context, and state-management approaches for long-running workflows, including recovery, data retention, access boundaries, and isolation between users or engagementsSet integration standards for MCP servers and tools used in authorized security workflows, including reconnaissance, scanners, controlled exploit tooling, and internal services Define permissions, approval requirements, auditability, and containment of failuresEstablish a balanced testing and evaluation strategy covering software correctness, agent behavior, security boundaries, and operational performance Define release criteria and ensure the team can demonstrate that they are metGuide production readiness and incident response, including observability, cost controls, staged delivery, rollback, and recovery Use operational evidence to prioritize improvements and technical debtPlan and prioritize technical delivery with product, security, and engineering stakeholders Break work into achievable milestones, delegate ownership, manage dependencies, and resolve technical and delivery impedimentsPersonally build working prototypes and production-grade slices of the solution, taking them through implementation, testing, and deployment Lead complex troubleshooting and develop other engineers through design reviews, coaching, and constructive feedbackImprove engineering processes, contribute to technical hiring, and communicate progress, risks, alternatives, and decisions clearly to customers and the teamRequirementsSubstantial experience delivering and operating production software, typically five or more years, including at least one year shipping LLM-based agents to production You also bring a demonstrated record of technical leadership and team deliveryStrong programming skills and production depth in at least one general-purpose language, with practical agent development experience You can work across language boundaries, guide technology choices, and help the team adopt unfamiliar tools You personally deliver working prototypes and production-grade implementationsExperience designing system components or complete solutions, evaluating architectural alternatives, and making decisions against business needs and non-functional requirementsDeep experience with cloud managed services for AI hosting (e.g., Bedrock, Azure AI Foundry, Vertex AI), including runtime, state, identity, integration, and observability concerns, and evidence of leading a team through adoption of an unfamiliar platformPractical expertise in MCP, tool orchestration, context and memory management, and agent evaluation, supported by a strong understanding of distributed-system failures and security boundariesExperience establishing or improving testing, CI/CD, observability, and engineering practices You can explain how these practices improved quality, delivery, or operational outcomesExperience leading technical discussions with customers, presenting alternatives, and aligning stakeholders on scope, priorities, risks, and trade-offsThe ability to plan team delivery, delegate effectively, resolve disagreements and impediments, mentor engineers, and conduct technical interviewsSound judgment when adopting AI development tools: clear expectations for data access, permissions, review, and verification, with outcomes assessed through evidenceEnglish proficiency at B2 level or higherNice to haveExperience leading engineering work in application security, penetration testing, red-teaming, or security automation within an authorized scopeExperience designing platforms for sandboxed code execution, browser agents, or autonomous tool orchestrationExperience establishing reusable agent components, evaluation practices, or operational standards used by multiple teamsExperience taking a new product or technical capability from initial design through launch and ongoing operationWe offerCONTINUOUS UPSKILLING, LEARNING & DEVELOPMENTDiversity of tasks and projectsAssessment center for objective review of competency levelPersonal development planMentoring programs and leadership developmentCertification and professional development supportAccess to learning platforms including more than 2,500 internal coursesEnglish courses taught by certified teachersCORPORATE BENEFITSExtra leave daysReferral bonusesCOMPENSATION PACKAGECompetitive compensation paid in USDRegular salary and performance reviewsMEDICAL & HEALTHCAREPrivate health insuranceWell-being eventsWORKING ENVIRONMENTRecreation areas and kitchensTea, coffee and snacksSports equipment and game consolesIT EquipmentMicrosoft’s Software Assurance Home Use Program (HUP)Please note that our Talent Attraction Team reviews applications and CVs submitted in English.EPAM is global leader in AI transformation engineering and integrated consulting, serving Forbes Global 2000 companies and ambitious startups. With over thirty years of expertise in custom software, product and platform engineering, we empower our clients to become AI-Native enterprises, driving measurable value from innovation and digital investments.