Lead Python AI Engineer

EPAM Systems Inc; United States; On-site; USD 150,000 - 230,000; Full time

Job summary

EPAM Systems is seeking a Lead AI Engineer to design and deliver production-grade AI agents and data-integrated tool APIs in a cloud-native Python environment.

You will shape agent architecture, ensure observability, and work with distributed stakeholders to ship high-quality outcomes across platforms.

Qualifications

• 5+ years of production software development experience with Python.
• 2+ years building LLM integrations or AI agents.
• Lead-level technical leadership with design and code ownership.
• Strong Python 3.11+ with AsyncIO and clean architecture.
• Strong FastAPI skills for backend microservices and tool APIs.
• Strong SQL for analytical queries.
• Solid Docker skills for packaging and running services.
• Experience with Google Agent Development Kit for agents/tools.
• Model Context Protocol experience for safe data access.
• Upper-Intermediate English (B2) for cross-team collaboration.

Responsibilities

• Design production-grade AI agent architectures and tool interfaces.
• Build scoped AI agents with tool-calling and structured outputs.
• Expose enterprise datasets via read-only Model Context Protocol servers.
• Develop FastAPI services and asynchronous task handlers.
• Write and optimize SQL for cost datasets with partitioning.
• Implement health probes, JSON logging, and tracing for observability.
• Establish tests alongside capability modules to protect flows.
• Coordinate peer code reviews and maintain monorepo standards.
• Collaborate with product and architecture to deliver measurable results.

Skills

Python

AsyncIO

LLM integrations

Agent orchestration

Project ownership

Code quality leadership

SQL

English communication

Clean architecture

Cross-team collaboration

Tools

FastAPI

Docker

Google Agent Development Kit

LangChain

Job description

We are seeking a Lead AI Engineer to design and deliver production-grade AI agents and data-integrated tool APIs in a cloud-native Python environment. You will shape agent architecture, ensure reliable observability and schema-compliant access patterns, and collaborate with distributed stakeholders to ship high-quality outcomes.

Responsibilities

• Design production-grade AI agent architectures and tool interfaces aligned to platform standards
• Build scoped AI agents with tool-calling, structured outputs, and robust prompt/tool orchestration
• Implement read-only Model Context Protocol servers that securely expose enterprise datasets to agents
• Develop FastAPI services and asynchronous task handlers to support low-risk actions and ticket generation
• Write and optimize SQL for normalized cost datasets while respecting partitioning and clustering constraints
• Implement health and readiness probes, structured JSON logging, and distributed tracing for observability
• Establish unit and integration tests co-located with capability modules to protect critical flows
• Coordinate peer code reviews and enforce monorepo structure and engineering excellence practices
• Collaborate with product and architecture stakeholders to refine requirements and deliver measurable results

Requirements

• 5+ years of production software development experience with Python 2+ years of hands-on experience building LLM integrations or AI agents
• Lead-level technical leadership experience guiding design and code quality
• Strong project ownership skills for delivering production-grade services end to end
• Advanced Python 3.11+ skills with AsyncIO and clean architecture practices
• Strong FastAPI skills for building backend microservices and tool APIs
• Strong SQL skills for authoring and optimizing analytical queries
• Solid Docker skills for packaging and running services reliably
• Hands-on Google Agent Development Kit experience for agent and tool development
• Model Context Protocol experience implementing safe, read-only data access patterns
• Upper-Intermediate English proficiency (B2) for cross-team collaboration

Nice to have

• Google Cloud BigQuery experience optimizing large partitioned datasets
• Google Vertex AI experience integrating hosted models and evaluation workflows
• CI/CD experience building automated test and release pipelines
• Terraform experience provisioning and managing cloud infrastructure as code
• LangChain experience building agent workflows and tool integrations