Principal Forward Deployed Engineer (relocation to Bulgaria)

EPAM Systems; Al Khobar; Hybrid; SAR 450,000 - 637,000; Full time

Benefits offered by this job

Hybrid By Design

Modern Sofia office

Professional trainings

Global collaboration

Flexible schedule

Job summary

EPAM Systems is seeking a Principal Forward Deployed Engineer to design and ship AI-native systems, including agents, workflows, RAG, and integration harnesses. You will write production-grade Python code for integrations and data access, and work directly with SMEs and end-users to define impactful use cases.

You will lead development, collaborate with global teams, and ensure engineering excellence with TDD and CI/CD while navigating the challenge of delivering robust AI solutions and

Qualifications

• 7+ years of software engineering experience building production AI/LLM apps

Responsibilities

• Design, build and ship end-to-end AI-native systems including agents, workflows, RAG and integration harnesses
• Write production-grade Python code for integrations, APIs, data access and deployment
• Work directly with SMEs and end-users through interviews, user acceptance testing and workflow observations
• Engage early in projects to shape use cases and check technical feasibility
• Build evaluation pipelines and use them to prove system utility
• Design for failure in the agent loop with retries, model fallbacks, cost limits and human-in-the-loop actions
• Capture domain expertise and repeatable workflows to ensure success across engagements and troubleshoot with the team
• Ensure adherence to engineering excellence standards including test-driven development and CI/CD

Skills

Python

English communication

Client collaboration

Problem solving

Leadership

Education

Bachelor's degree in Computer Science or related field

Tools

LangChain

LangGraph

Semantic Kernel

LLM providers

Vector databases

Job description

We are looking for a Principal Forward Deployed Engineer to join our team with eventual relocation to Bulgaria. EPAM is renowned for delivering cutting-edge technological solutions to transform businesses worldwide.

We are building AI-native solutions for our clients - products where LLM and its harness are the core of the value. This is a builder's role: you and your team are responsible for building agentic systems, writing the production code, and standing up the evals and observability. You will work closely with SMEs and end-users to understand where the real value lies, and you design the feedback loops.

The deadline for submission is 01.12.2026.

Responsibilities

• Design, build and ship end-to-end AI-native systems including agents, workflows, RAG and integration harnesses
• Write production-grade Python code for integrations, APIs, data access and deployment
• Work directly with subject matter experts and end-users through interviews, user acceptance testing and workflow observations
• Engage early in projects to shape use cases and check technical feasibility
• Build evaluation pipelines and use them to prove system utility
• Design for failure in the agent loop by implementing retries, model fallbacks, cost limits and human-in-the-loop actions
• Capture domain expertise and repeatable workflows to ensure success across engagements. Troubleshoot and resolve technical challenges in collaboration with the broader team
• Ensure adherence to engineering excellence standards including test-driven development and continuous integration practices

Requirements

• 7+ years of software engineering experience with a strong track record of building production AI and LLM applications
• Expert-level Python skills and solid software engineering fundamentals
• Hands-on experience with agentic frameworks such as LangChain, LangGraph or Semantic Kernel and major LLM providers
• Strong RAG and retrieval skills including vector databases, embeddings, hybrid search and context management
• Production deployment experience on major cloud platforms like AWS, Azure or GCP with containerization and CI/CD
• Proven experience evaluating generative AI quality using custom evaluation frameworks and observability tools
• Proven capability to work closely with clients, lead discovery conversations and explain technical trade-offs to diverse audiences
• Strong agent-design judgment and sound engineering judgment under ambiguity to balance speed, quality and scope
• C1 level English language proficiency
• An academic degree in Computer Science, Software Engineering or a related field

Nice to have

• Experience designing experiments, A/B testing and iterating on AI products against real user behavior
• Strong background in NLP, Data Science or applied machine learning with experience moving models into production
• Familiarity with Model Context Protocol (MCP), Agent-to-Agent (A2A), Agent Skills and emerging agent standards
• Experience with enterprise AI platforms such as AWS Bedrock AgentCore, Databricks Genie or Microsoft Foundry
• Exposure to AI governance, security and compliance including guardrails and prompt-injection prevention

We offer

• Opportunity to Engineer your Future and to drive the world’s digital transformation with top industry clients
• Personal development program that will allow you to be valued for your strengths
• Wide range of professional trainings and workshops
• Being part of a collaborative, fast-growing, and innovative design team
• Established and accelerated growth toward different career paths, competencies, and roles
• Broad projects variety and possible mobility between projects over the time
• Collaboration in a multicultural environment and exchange of best practices with colleagues around the world
• Varied social benefits, Sports, Transportation and Health programs
• Work-life balance and flexible schedule, team buildings and sport opportunities
• Modern office/collaboration spaces (incl. new Infinity Tower business center, Sofia)
• Hybrid By Design - we provide you with the best productivity options from the 2 worlds. Meet, socialize and enjoy F2F time with your colleagues, while working from the modern EPAM's office for a few days per week and benefit from the EPAM's virtual working environment - making you able to be productive and work from remote for the rest of the week