EPAM Systems
18 hours ago
Lead AI Agentic Developer
Sign up to save this job, get alerts, and apply with an optimized CV.
Company information
- Company
- EPAM Systems
- Location
- Argentina Argentina
- Posted
- 18 hours ago
Job description
We are building a Lead AI Agentic Developer role to lead AI-powered engineering initiatives that elevate the retail experience through generative AI. You will own agentic and RAG solutions end-to-end across Python/FastAPI, React/TypeScript, and Google Cloud Vertex AI, with strong observability and cost controls.
Responsibilities
- Design, build, deploy, and support AI-powered applications using Python/FastAPI backends, React/TypeScript frontends, and Google Cloud Vertex AI while following best practices and quality standards
- Own GenAI systems end to end, covering architecture choices, feature delivery, operational readiness, production support, and cost optimization
- Apply AI-augmented engineering workflows and collaborate effectively with AI coding assistants such as Claude Code and GitHub Copilot to speed delivery and improve code quality
- Collaborate with solution engineers, architects, and product teams to produce technical design specifications and confirm alignment with architectural standards, non-functional requirements, and business needs
- Implement LLM orchestration approaches including prompt engineering, retrieval-augmented generation (RAG), multi-agent workflows, and structured-output generation
- Create and maintain observability pipelines for AI platforms, including trace analysis, token-usage tracking, cost monitoring, and quality metrics
- Provide technical leadership and mentorship to help teammates grow in agentic development practices, prompt-engineering techniques, and AI-tool integration
- Evaluate cross-platform trade-offs across backend technologies, frontend technologies, and AI services to maintain architectural consistency and identify optimization opportunities
- Troubleshoot defects, perform root-cause analysis, and code, test, and deliver full-stack enhancements
- Communicate risks, blockers, and schedule impacts early to ensure on-time delivery of AI initiatives and drive resolution to protect commitments
- Coordinate multiple deliverables across services and platforms, handle operational requests, and resolve production issues efficiently
- Use observability and monitoring tools including LangFuse, Grafana, Dynatrace, and Splunk to review dashboards, investigate anomalies, monitor AI-model performance, and track cost metrics
Requirements
- Proven background of 5+ years in software development, including hands-on generative AI and agentic development with AI coding assistants such as Claude Code, GitHub Copilot, Cursor, and Windsurf
- Deep expertise in generative AI application development, GenAI design patterns, and GenAI cloud platforms including Google Cloud Vertex AI, Gemini, Anthropic Claude, and OpenAI
- Hands-on experience with LLM observability and tracing using Langfuse, LangSmith, or similar platforms
- Strong skills in prompt-engineering methods such as chain-of-thought prompting, few-shot learning, and structured outputs
- Solid understanding of LLM orchestration, RAG architectures, multi-agent systems, tool calling, and agent evaluation
- Advanced proficiency in Python, FastAPI, asynchronous programming, Pydantic, and SQLAlchemy ORM
- Strong background with MySQL and PostgreSQL, including query optimization and Alembic migrations
- Practical knowledge of authentication and authorization patterns including OAuth 2.0, Okta, JWT, and role-based access control (RBAC)
- Proven experience with Docker, Docker Compose, Kubernetes, and container orchestration
- Hands-on frontend skills with React, TypeScript, Zustand state management, and Material UI (MUI)
- Working knowledge of data-visualization libraries including Recharts and D3.js
- Strong experience with Google Cloud Platform, including Vertex AI, Cloud Run, BigQuery, Cloud Storage, and IAM, plus Git, CI/CD, GitHub Actions, and ArgoCD
- English proficiency at B2 level (Upper-Intermediate) or higher
Required skills
- mysql
- docker
- ci/cd
- mentorship
- software development
- generative ai
- react
- typescript
- python
- kubernetes
- prompt engineering
- git
- github actions
- google cloud platform
- postgresql
- grafana
- architects
- architecture
- technical leadership
- observability
- gemini
- tool calling
- fastapi
- dynatrace
- monitoring tools
- claude code
- windsurf
- oauth 2.0
- jwt
- splunk
- cost optimization
- d3.js
- iam
- retail experience
- rag
- openai
- cloud storage
- bigquery
- container orchestration
- authentication
- multi-agent systems
- resolution
- argocd
- dashboards
- english proficiency
- rag architectures
- ai services
- cursor
- operational readiness
- production support
- feature delivery
- product teams
- frontend technologies
- okta
- b2 level
- asynchronous programming
- cloud run
- material ui
- rbac
- query optimization
- non-functional requirements
- quality metrics
- github copilot
- anomalies
- backend technologies
- retrieval-augmented generation
- root-cause analysis
- docker compose
- authorization patterns
- tracing
- solution engineers
- anthropic claude
- cost controls
- risks
- llm orchestration
- architectural standards
- business needs
- pydantic
- langsmith
- role-based access control
- langfuse
- multi-agent workflows
- recharts
- mui
- agentic development
- commitments
- on-time delivery
- agent evaluation
- technical design specifications
- blockers
- alembic migrations
- operational requests
- architectural consistency
- few-shot learning
- ai coding assistants
- ai-powered applications
- optimization opportunities
- production issues
- ai initiatives
- google cloud vertex ai
- trace analysis
- llm observability
- genai systems
- observability pipelines
- cost metrics
- multiple deliverables
- ai-augmented engineering
- schedule impacts
- ai agentic developer
- structured-output generation
- token-usage tracking
- agentic development practices
- ai-tool integration
- cross-platform trade-offs
- troubleshoot defects
- full-stack enhancements
- ai-model performance
- genai design patterns
- genai cloud platforms
- prompt-engineering methods
- chain-of-thought prompting
- sqlalchemy orm
- zustand state management
- data-visualization libraries
Interested in this position?
Create your free account and tailor your CV to match this job.