Lead Full-Stack - AI Engineer (Relocation to Qatar)

EPAM Systems; Georgia; On-site; USD 120,000 - 180,000; Full time

Job summary

EPAM Systems in the United States is seeking a Lead Full-Stack Engineer to join our team with relocation to Qatar. The role focuses on delivering AI-enabled software through Java/Spring Boot microservices, RAG and agentic architectures, and cloud-native platforms.

You will guide design decisions, implement guardrails, collaborate with platform/SRE teams, and mentor squads while ensuring secure, observable, and scalable solutions deployed on AKS and Azure.

Qualifications

• 5+ years of hands-on development in Core Java, Spring Boot, and web services.
• At least 1 year of leadership experience.
• Hands-on delivery exposure to LLMs, RAG, and agentic systems.
• Understanding of cloud-native architecture, Oracle/PL/SQL, and Kafka.
• Knowledge of Spec Driven Development (SDD) and guardrails.
• Experience with self-hosted models and prompt engineering.
• Proficiency in English and ability to work in a global team.

Responsibilities

• Contribute to pragmatic AI architectures integrated into cloud-native microservices.
• Implement and apply SDD specs/templates and governance gates.
• Build and maintain agentic use cases and guardrails.
• Deliver production solutions with LLM integrations in Java/Spring Boot services.
• Implement observability, rollout, and CI/CD for prompts and models on AKS/Azure.
• Track adoption, productivity, quality and risk KPIs for AI-enabled delivery.
• Participate in playbooks, training, and team mentoring.
• Ensure responsible AI controls and data handling in line with policies.

Skills

Core Java

Spring Boot

Microservices

Web services

LLM integrations

RAG/agents

Cloud-native

Kafka

Oracle/PL/SQL

GitLab

Azure AKS / Web Apps

CI/CD

Leadership experience

English communication

Tools

Kafka

GitLab

Azure DevOps

Oracle

LangChain

AKS

Azure Web Apps

Job description

We are looking for a Lead Full-Stack Engineer to join our team with eventual relocation to Qatar. EPAM is renowned for delivering cutting-edge technological solutions to transform businesses worldwide. This is an onsite position in Qatar, requiring 3 days per week to be worked in the client's office, and the rest to be worked anywhere in Qatar.

Responsibilities

• Contribute to pragmatic AI architectures (RAG/agents/copilots/automation) integrated into cloud-native microservices (including Kafka) and enterprise data platforms (e.g., Oracle), guiding decisions on when to use RAG vs agents vs conventional approaches
• Implement and apply SDD specs/templates, support governance/quality gates, and help embed SDD into delivery workflows
• Build and maintain agentic use cases, including hands‑on ability to run/write agents and implement guardrails defined by the program
• Deliver production solutions (LLM integrations, retrieval, embeddings/vector stores where relevant) embedded into Java/Spring Boot services
• Implement observability, rollout/versioning, and CI/CD for prompts/specs/models, deploying and operating on AKS and Azure hosting with guidance from platform/SRE teams
• Contribute to tracking adoption, productivity, quality, and risk KPIs for AI-enabled delivery
• Participate in playbooks, training, documentation, and team mentoring, sharing patterns and examples across squads
• Ensure responsible AI controls, data handling constraints, and agent guardrails are applied in line with company policies and engineering standards

Requirements

• 5+ years of hands‑on development experience in Core Java, Spring/Spring Boot, and web services/microservices
• At least 1 year of relevant leadership experience
• Hands‑on delivery exposure to LLMs, RAG, and agentic systems (production or strong pilot/enterprise PoC experience)
• Understanding of cloud‑native architecture, database concepts (preferably Oracle/PL/SQL), and Kafka/GitLab
• Knowledge of AI concepts, especially Spec Driven Development (SDD), with working experience in running and writing agents and implementing guardrails
• Background in LLM providers and/or self‑hosted models, prompt engineering, and an evaluation/testing mindset
• Practical expertise in applying SDD (spec‑driven ways of working) in a team setting
• Hands‑on capability to build and integrate agentic and/or RAG capabilities into real engineering workflows
• Familiarity with Azure (AKS and/or Azure Web Apps) and CI/CD with GitLab (Azure DevOps is a plus)
• Competency in balancing cost, productivity, quality, and risk when implementing LLM/agentic solutions (with guidance where needed)
• Production mindset covering testing, observability, safe rollout, and secure‑by‑design implementation
• Skills in communication and the capability to work in a global team
• Proficiency in English at an Upper‑Intermediate level (B2) or higher

Nice to have

• Knowledge of React
• Familiarity with Ansible
• Experience with Kubernetes
• Background in LangChain