AI Platform Engineer

EPAM Systems Inc; United States; Remote; USD 120,000 - 190,000; Full time

Job summary

EPAM Systems is seeking an AI Platform Engineer to design Python SDKs and platform libraries that empower teams to ship, run, and scale agentic and GenAI solutions on Google Cloud. You will define developer APIs and integrate with LLMs and enterprise systems to enable reliable deployment.

You will also contribute to reusable RAG components, retrieval patterns, and establish guardrails for production LLM and agent traffic, while collaborating with Cloud/DevOps to deploy on GCP using Terraform.

Qualifications

• 2+ years of hands-on Python experience building libraries, SDKs, or frameworks.

Responsibilities

• Design Python SDKs, ADKs, and platform libraries that support agentic and GenAI development.

Skills

Python

SDKs/Frameworks

Agentic AI

Leadership

Production at scale

FastAPI

Asyncio

Observability

English B2

Tools

Terraform

Docker

Jenkins CI/CD

Kubernetes

GCP Vertex AI

Job description

We are looking for an AI Platform Engineer to build Python SDKs and platform frameworks that help teams ship, run, and scale agentic and GenAI solutions on Google Cloud reliably. You will contribute to developer-facing APIs, reliability practices, and production guardrails across the platform.

Responsibilities

• Design Python SDKs, ADKs, and platform libraries that support agentic and GenAI development
• Build shared frameworks, abstractions, and tooling for AI agents, copilots, and GenAI applications
• Define SDK architecture, developer APIs, and integrations with LLMs and enterprise systems
• Develop reusable RAG components, retrieval building blocks, and prompt engineering primitives
• Design retrieval patterns using vector search and graph-native data sources for relationship-aware context
• Create clear documentation, samples, and reference implementations to encourage SDK/ADK adoption
• Collaborate with Cloud and DevOps partners to package, distribute, and deploy components on GCP using Terraform
• Establish versioning, testing, benchmarking, and quality gates for SDK releases
• Implement guardrails and safety controls for production LLM and agent traffic
• Improve CI/CD workflows and release automation with Jenkins and Docker

Requirements

• 2+ years of hands-on Python experience building libraries, SDKs, or frameworks
• Practical exposure to agentic AI, including building and orchestrating AI agents with some hands-on delivery
• Solid technical leadership skills to contribute to architecture decisions and support mentoring within the team
• Proven experience delivering agent-based or AI applications into production at scale
• Strong GCP Vertex AI experience for model serving and orchestration
• Strong API engineering skills with FastAPI and async-first REST design
• Strong infrastructure automation skills with Terraform, Docker, and Jenkins CI/CD
• Strong Python engineering skills with asyncio, type hints, dataclasses, Pydantic, and pytest
• Strong observability skills with structured logging, distributed tracing, and telemetry tools
• Strong problem-solving skills and an API/framework design mindset
• Upper-Intermediate English skills (B2) for daily collaboration and documentation
• Nice to have Google Agent Development Kit Google Cloud Platform AI Solution Engineering Kubernetes MLOps