Senior Backend Engineer: AI Pods & LLM Orchestration

EPAM Systems; Colombia; On-site; COP 120,000,000 - 180,000,000; Full time

Benefits offered by this job

Healthcare benefits

Competitive compensation

Global career opportunities

Paid time off

Learning and certification support

Volunteer opportunities

Job summary

EPAM Systems is seeking a Senior Backend Developer to join the AI Pods team. You will design and build robust backend API services and LLM orchestration layers, owning API contracts and end-to-end reliability.

You will integrate LLMs with secure, scalable architectures, implement RAG pipelines, and develop agent tools using LangChain, LangGraph and related frameworks, collaborating with cross-functional teams to deliver cutting-edge AI solutions.

Qualifications

• 3+ years of backend engineering experience in microservices
• Proficiency in Python for cloud-native APIs
• Experience with AWS, Docker, and container orchestration
• Knowledge of RESTful APIs and secure coding practices
• English proficiency at B2 level or higher

Responsibilities

• Design and build backend API services and LLM orchestration layers
• Own API contracts and service reliability end-to-end
• Integrate LLMs with secure, scalable systems
• Implement RAG pipelines with ingestion, embedding, retrieval
• Develop agent tools using LangChain, LangGraph, MCP
• Build orchestration frameworks for downstream developers
• Ensure security, observability, and test coverage
• Contribute to architecture decisions and standards
• Collaborate with frontend, data, and infrastructure teams

Skills

Python

Backend engineering

Microservices

AWS

Docker

ECS/EKS

RESTful APIs

Security best practices

English (B2+)

Tools

LangChain

LangGraph

LlamaIndex

LangSmith

OpenAI

OpenSearch

Amazon Kendra

Job description

EPAM Systems is seeking a Senior Backend Developer to join the AI Pods team. You will design and build robust backend API services and LLM orchestration layers, owning API contracts and end-to-end reliability.

You will integrate LLMs with secure, scalable architectures, implement RAG pipelines, and develop agent tools using LangChain, LangGraph and related frameworks, collaborating with cross-functional teams to deliver cutting-edge AI solutions.