Overview

We are hiring a Lead Python Developer with React to spearhead the build-out of an enterprise-grade agentic AI platform powered by Python and AWS. The platform coordinates AI agents to automate complex professional workflows. In this role, you will shape architectural direction, lead a team of engineers and safeguard production reliability across a multi-environment deployment pipeline. This hands-on leadership position blends deep backend engineering with modern AI/LLM integration know-how.

Responsibilities

  • Lead end-to-end delivery of an enterprise-grade agentic AI platform
  • Shape architectural direction and evolve the design of distributed systems
  • Coordinate AI agents to automate complex professional workflows
  • Safeguard production reliability across CI/INT/QA/PROD environments
  • Provide technical leadership and mentorship to a team of engineers
  • Run code reviews and oversee technical debt management
  • Evaluate architectural trade-offs to balance business and engineering priorities
  • Embed large language models into applications through prompt engineering and agent delegation patterns
  • Programmatically provision and govern cloud infrastructure across multiple accounts and environments
  • Establish and refine CI/CD pipelines along with automated deployment workflows

Requirements

  • 5+ years of hands-on backend engineering experience with deep proficiency in Python (3.11+), covering async/await patterns and Pydantic data modeling
  • Showcase of modular package design within a mono repo leveraging uv workspaces
  • Expertise in FastAPI for delivering production REST APIs with dependency injection, middleware and SSE streaming
  • Practical background in LLM / AI Agent Engineering, ideally with Anthropic Claude, spanning tool/skill orchestration and agent delegation
  • Solid command of AWS Cloud Services including EKS (Kubernetes), RDS (PostgreSQL) and S3, complemented by Redis, ECR and Cognito
  • Familiarity with AWS Bedrock and AgentCore for managed LLM hosting and serverless agent runtime environments
  • Qualifications in AWS CDK for Infrastructure as Code spanning multiple accounts and environments
  • Strong grasp of SQL and the data layer through SQLAlchemy (async), Alembic migrations and PostgreSQL
  • Competency in CI/CD workflows using GitHub Actions and Docker (multi-stage builds)
  • Demonstrated technical leadership in coaching engineers and steering architectural decisions
  • English proficiency at B2 level or higher

Nice to have

  • Flexibility to use React 18, Zustand and TanStack Query, paired with Vite for crafting modern TypeScript-based frontends
  • Skills in testing approaches with pytest (async, parallel), Playwright for E2E coverage and quality gate enforcement in CI pipelines
  • Knowledge of LLM observability platforms such as Langfuse or Promptfoo for tracing, evaluating and monitoring LLM behavior
  • Capability to implement distributed tracing and application monitoring with OpenTelemetry and Datadog
  • Background in security and compliance tooling such as SonarQube or Snyk, together with Artillery for load and performance testing
  • Proficiency in Jinja2 prompt templating for maintainable, template-driven prompt systems

[GTS] Benefits (generic, except India)

  • International projects with top brands
  • Work with global teams of highly skilled, diverse peers
  • Healthcare benefits
  • Employee financial programs
  • Paid time off and sick leave
  • Upskilling, reskilling and certification courses
  • Unlimited access to the LinkedIn Learning library and 22,000+ courses
  • Global career opportunities
  • Volunteer and community involvement opportunities
  • EPAM Employee Groups
  • Award-winning culture recognized by Glassdoor, Newsweek and LinkedIn