Senior AI Engineer

EPAM Systems, Inc.; United States; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Healthcare benefits

Employee financial programs

Paid time off and sick leave

Upskilling and certification courses

Job summary

EPAM Systems, Inc. seeks a Senior AI Engineer to design GenAI and agentic workflows that orchestrate models, tools, and enterprise data. You will productionize RAG, establish observability, and deliver robust Python services with FastAPI.

You will own end-to-end delivery, collaborate with product and engineering teams, implement guardrails and privacy controls, and help scale solutions across international projects.

Qualifications

• 3+ years delivering production AI/GenAI solutions.
• Ownership to lead technical decisions for agentic workflows.
• Advanced Python for production software engineering and data handling.
• Experience with tool orchestration, structured outputs, state/memory.

Responsibilities

• Design and productionize GenAI and agentic systems.
• Develop agent orchestration patterns for planning, routing, tool calling, and recovery.
• Build reusable agent tools, APIs, and connectors with clear schemas and least-privilege access.
• Implement observability for prompts, traces, retrieval, and costs.

Skills

GenAI systems

Python production

FastAPI

Agent orchestration

RAG engineering

Observability

Evaluation frameworks

Security guardrails

Tools

FastAPI

Embeddings

Vector databases

Cloud AWS

Job description

We are seeking a Senior AI Engineer to design and productionize GenAI and agentic solutions that orchestrate models, tools, and enterprise data to solve complex, multi-step workflows. You will build reliable RAG, evaluation, and observability capabilities and deliver robust Python services.ResponsibilitiesDesign and productionize GenAI and agentic systems that orchestrate models, tools, enterprise data, state and memory, and human inputDevelop agent orchestration patterns for planning, routing, tool calling, structured outputs, workflow graphs, handoffs, retries, and recoveryBuild reusable agent tools, APIs, and connectors with clear schemas, authentication, permissions, sandboxing, and least-privilege accessBuild and optimize RAG and enterprise search using embeddings, vector databases, hybrid retrieval, metadata filtering, reranking, grounding, and citationsCreate evaluation and test frameworks that measure task completion, groundedness, retrieval quality, tool-use accuracy, robustness, and end-to-end outcomesImplement observability for prompts, traces, retrieval, model behavior, token usage, cost, latency, failures, and user feedback to drive improvementsDevelop production-grade Python and FastAPI services with automated testing, CI/CD, load testing, caching, fallbacks, and performance optimizationApply Responsible AI and security practices including guardrails, content filtering, privacy controls, authorization, auditability, and escalation pathsCollaborate with product, engineering, and domain partners to translate needs into measurable workflows, prototype quickly, and scale successful solutionsRequirements3+ years experience delivering production-ready AI or GenAI solutionsSenior-level ownership skills to lead technical decisions for agentic workflowsStrong project execution skills to take prototypes to reliable production releasesAdvanced Python skills for production software engineering and data handlingFastAPI development skills including async APIs, testing, and service designAgent orchestration skills with tool/function calling, structured outputs, state and memory, retries, and human-in-the-loop controlsRAG engineering skills using embeddings, vector databases, hybrid retrieval, reranking, grounding, and citationsEvaluation framework skills for LLM and agentic quality, safety, and regression testingObservability skills for prompts, traces, tool calls, retrieval, cost, latency, and failuresResponsible AI and security skills including guardrails, prompt-injection defenses, and privacy controlsUpper-Intermediate English skills (B2, Upper-Intermediate)Nice to haveAmazon Web Services skills including cloud-native deployment patternsData governance skills for enterprise content and access controlsGen AI assisted development skills to accelerate delivery and maintain qualityMachine learning engineering skills for model evaluation and system integrationResponsible AI skills for safety, compliance, and risk managementWe offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedIn