Chief Forward Deployed Engineer

• 7+ years of engineering experience with a strong recent track record building production AI/LLM applications
• Strong agent-design judgment, matching the harness to task context, failures, and policies
• Ability to operate close to clients, lead discovery and feasibility conversations, and explain technical trade-offs to technical and non-technical audiences
• Hands-on experience with agentic frameworks (LangChain, LangGraph, Semantic Kernel, or similar) and major LLM providers (OpenAI, Anthropic, Google Gemini)
• Expert-level Python skills and solid software engineering fundamentals
• Strong RAG and retrieval skills including vector databases, embeddings, hybrid search, re-ranking, chunking, and context management
• Proven experience evaluating generative AI quality using LLM-based evaluation, heuristics, custom eval frameworks, and observability/tracing tools (LangSmith, Arize Phoenix, Langfuse, or similar)
• Production deployment experience on at least one major cloud (AWS, Azure, or GCP) with containerization and CI/CD
• Sound judgment under ambiguity regarding scoping, sequencing, and balancing speed, quality, and scope
• English language proficiency at C1 level

Nice to have:

• Experience designing experiments, A/B testing, and iterating on AI products based on user behavior and business metrics
• Background in NLP, Data Science, or applied ML with experience moving models into production
• Familiarity with MCP, A2A, Agent Skills, and emerging agent standards
• Experience with enterprise AI platforms (AWS Bedrock AgentCore, Databricks Genie, Microsoft Foundry, Gemini Enterprise)
• Exposure to AI governance, security, and compliance (guardrails, prompt-injection prevention)
• Prior client-facing or pre-sales experience in consulting or services contexts

• Design, build, and ship AI-native systems end-to-end, including agents, workflows, RAG, and the harness (custom tool calling, sandboxing, context engineering, sub-agents, caching, compaction)
• Build evaluation pipelines and use them to prove system usefulness
• Design for failure in the agent loop, including retries, model fallbacks, cost limits, and human-in-the-loop on consequential actions
• Capture domain expertise and repeatable workflows to transfer knowledge across engagements
• Engage early to shape use cases and check technical feasibility
• Write production-grade Python code for integrations, APIs, data access, and deployment
• Work directly with SMEs and end-users through interviews, user acceptance testing (UAT), and workflow observation to validate system fit

EPAM is a leading global provider of digital platform engineering and development services. The company embraces a dynamic and inclusive culture and collaborates with multinational teams on innovative projects. Candidates will join a dedicated, creative, and diverse community. No matter the location, employees have opportunities to learn and grow.