Remote Lead Python AI Engineer: Scalable AI APIs & LLMs

EPAM Systems; Newtown (PA); Remoto; USD 130.000 - 160.000; Tempo pieno

Vantaggi offerti da questo lavoro

Health Insurance

401(k) Matching

Paid Time Off

Life Insurance

Dental Insurance

Employee Discounts

Learning & Development

Descrizione del lavoro

EPAM Systems is seeking a Lead Python AI Engineer to build robust, AI-powered API services and agentic workflows that bridge traditional backends with modern language models. The role focuses on secure, scalable LLM interactions with internal systems, vector databases, and external tools via orchestration frameworks.

We treat LLMs as components in a secure distributed system, valuing production-grade AI integration, observability, and graceful failure handling.

Competenze

• 7+ years backend engineering with Python
• Experience with microservices and distributed systems
• Hands-on AWS, Docker, ECS/EKS and RESTful APIs
• Experience integrating AI SDKs in production
• Familiarity with AI evaluation tools and observability
• Experience with vector databases and RAG pipelines

Mansioni

• Own API contracts and service reliability end-to-end
• Integrate LLMs with secure, observable backends
• Design and build scalable backend API services and LLM orchestration layers
• Implement RAG pipelines for document ingestion, embedding and retrieval
• Develop and connect agent tools using LangChain, LangGraph
• Ensure security, privacy, and test coverage across workflows
• Contribute to architecture decisions and engineering standards
• Collaborate with frontend, data, and infra teams

Conoscenze

Python

API design

Distributed systems

Microservices

Cloud (AWS)

Security best practices

LangChain

LangGraph

Observability

RAG pipelines

Formazione

Bachelor's degree in CS or related field

Strumenti

Docker

ECS/EKS

RESTful APIs

AI SDKs in production

Kendra/OpenSearch

MCP

LangSmith/Langfuse/Arize

Descrizione del lavoro

EPAM Systems is seeking a Lead Python AI Engineer to build robust, AI-powered API services and agentic workflows that bridge traditional backends with modern language models. The role focuses on secure, scalable LLM interactions with internal systems, vector databases, and external tools via orchestration frameworks.

We treat LLMs as components in a secure distributed system, valuing production-grade AI integration, observability, and graceful failure handling.