Job Description, Responsibilities & Requirements
About the Position
We are seeking a Lead Forward Deployed Engineer to join our team focused on developing AI agents, along with the backend and frontend for related applications. With 20+ agents launched, we accelerate innovation across critical industries. You'll work in a high-impact, high-autonomy environment, taking projects from concept to production.
Responsibilities
- Collaborate with business stakeholders, product teams, and domain experts to understand requirements and translate them into practical technical solutions that drive measurable business outcomes
- Design and implement backend, full-stack applications, AI agents, and platform components, supporting rapid development and deployment of GenAI use cases
- Support delivery of solutions across the lifecycle - from prototyping through production rollout and iteration - ensuring reliability and usability in real-world environments
- Apply current LLM patterns such as RAG, retrieval, routing, tool-use, agent workflows, and evaluation approaches to deliver reliable and efficient AI systems
- Build and maintain developer tooling, CI/CD pipelines, and observability practices to support safe, fast, and stable iteration
- Follow strong engineering practices, including modularity, maintainability, and production readiness, while applying secure SDLC and privacy-by-design standards
- Contribute as a hands-on engineer within the team, supporting implementation, collaborating with peers, and helping resolve technical challenges
- Document and share learnings from implementations to contribute to team knowledge and incremental improvements in delivery practices
Requirements
- 5+ years of professional software engineering experience contributing to delivery of production systems
- At least 1 year of relevant leadership experience
- Strong full-stack development skills with working knowledge of backend and frontend development
- Background in building AI agents using TypeScript,.NET, or Go
- Proficiency in cloud platforms such as AWS, Azure, or GCP, with a proven track record delivering secure, reliable, cloud-native systems
- Exposure to AI/LLM-based solutions (e.g., using APIs or basic RAG patterns) in practical implementations
- Basic knowledge or exposure to at least one business domain
- Capability to collaborate with stakeholders and translate business requirements into technical solutions
- Excellent problem-solving and communication skills, with ability to work effectively within a team
- Strong English communication skills (B2 level or higher)
Nice to Have
- Familiarity with LangChain, LangGraph, and MCP, along with vector/RAG systems and OpenSearch
- Expertise in evaluation frameworks and advanced LLM patterns (orchestration, tool use, fine-tuning, model adaptation)
- Exposure to machine learning workflows, including training, deployment, and monitoring
- Understanding of CI/CD, Infrastructure as Code, and observability practices
- Awareness of secure SDLC, privacy considerations, and regulatory or compliance standards (e.g., SOC 2, HIPAA)
We Offer
- Opportunity to work remotely from Türkiye
- Be part of a team that accelerates innovation across critical industries
About the Company
EPAM Systems is a global software engineering and product development company, delivering digital platforms and solutions to the world's leading companies.