AI Engineer

EPAM Systems, Inc.; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Learning & development programs

Global career opportunities

Job summary

EPAM Systems, Inc. seeks an AI Engineer to design and productionize GenAI and agentic workflows that orchestrate models, tools, data, state, and human input across multi-step tasks.

You will build RAG search, observability, and evaluation frameworks, while applying Responsible AI and security practices. Strong Python, FastAPI, and CI/CD expertise are required for scalable production services.

Qualifications

• 2+ years delivering production-ready AI or GenAI solutions.
• Experience with tool/function calling, routing, and structured outputs.
• Strong Python skills for production services and asynchronous workflows.
• API engineering with FastAPI, automated testing, and CI/CD practices.
• Strong RAG and vector database skills including embeddings, hybrid retrieval, reranking, and citations.
• Security and Responsible AI skills including guardrails and privacy controls.
• Upper-Intermediate English (B2) proficiency.

Responsibilities

• Design and productionize GenAI and agentic systems that orchestrate models, tools, data, state, and human input across multi-step workflows.
• Develop agent orchestration patterns including planning, routing, structured outputs, workflow graphs, retries, error recovery, and human-in-the-loop controls.
• Build RAG and enterprise search solutions using embeddings, vector databases, hybrid retrieval, metadata filtering, query transformation, reranking, grounding, and citations.
• Create evaluation and test frameworks measuring task completion, groundedness, retrieval quality, tool-use accuracy, safety, robustness.
• Implement observability for prompts, traces, retrieval, tool calls, token usage, cost, latency, failures, and user feedback.
• Develop production-grade Python and FastAPI services with automated tests, CI/CD, caching, fallbacks, and performance and cost optimization.
• Apply Responsible AI and security practices including guardrails, content filtering, privacy controls, least-privilege access, auditability, and escalation paths.

Skills

Python

Asynchronous programming

Leadership

Cross-functional collaboration

English communication

Tools

FastAPI

Vector databases

Embeddings

Retrieval-augmented generation

Git

CI/CD

Job description

We are seeking an AI Engineer to design and deliver production-grade GenAI and agentic solutions that connect models, tools, and enterprise data to complete complex workflows. You will build reliable orchestration, RAG search capabilities, and evaluation/observability to improve quality and safety.ResponsibilitiesDesign and productionize GenAI and agentic systems that orchestrate models, tools, data, state, and human input across multi-step workflowsDevelop agent orchestration patterns including planning, routing, structured outputs, workflow graphs, retries, error recovery, and human-in-the-loop controlsBuild RAG and enterprise search solutions using embeddings, vector databases, hybrid retrieval, metadata filtering, query transformation, reranking, grounding, and citationsCreate evaluation and test frameworks that measure task completion, groundedness, retrieval quality, tool-use accuracy, safety, robustness, and regressionImplement observability for prompts, traces, retrieval, tool calls, token usage, cost, latency, failures, and user feedback to drive continuous improvementDevelop production-grade Python and FastAPI services with automated tests, CI/CD, caching, fallbacks, and performance and cost optimizationApply Responsible AI and security practices including guardrails, content filtering, privacy controls, least-privilege access, auditability, and escalation pathsBuild reusable tools, APIs, and connectors with clear schemas, permissions, authentication, sandboxing, and least-privilege accessCollaborate with product, engineering, and domain experts to define measurable outcomes, prototype solutions, and scale successful capabilitiesRequirements2+ years of experience delivering production-ready AI or GenAI solutionsHands-on agentic application experience with tool/function calling, routing, and structured outputsSolid leadership skills to collaborate with cross-functional partners and align on measurable outcomesWorkflow delivery experience translating business needs into agentic workflows from prototype to scaleStrong Python skills for production services, asynchronous workflows, and data handlingAPI engineering skills with FastAPI, automated testing, and CI/CD practicesStrong RAG and vector database skills including embeddings, hybrid retrieval, reranking, and citationsSecurity and Responsible AI skills including guardrails, privacy controls, and prompt-injection defensesStrong problem-solving skills for reliability, error recovery, and performance optimizationUpper-Intermediate English (B2) proficiencyNice to haveAmazon Web Services (AWS) experience with managed GenAI platforms such as BedrockData governance knowledge for permissions, auditability, and enterprise controlsGen AI assisted development practices for accelerating delivery with quality safeguardsMachine learning engineering experience for model evaluation and deployment readinessResponsible AI experience with safety testing and governance processesWe 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