Lead AI Agent Engineer – Full-Stack & Data (Oil & Gas)

EPAM Systems, Inc.; México; A distancia; MXN 1.200.000 - 2.100.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare benefits

Paid time off and sick leave

Upskilling, reskilling and certs

Global career opportunities

Descripción de la vacante

EPAM Systems, Inc. seeks a Lead Full-Stack, Data and AI Agent Engineer to build a production-grade agentic AI platform for upstream oil & gas operations. You will evolve the deep-agent core that translates engineers’ questions into safe, schema-aware SQL and multi-step workflows.

You will design FastAPI endpoints, ensure injection-safe SQL, and integrate AWS Bedrock with LangChain workflows. This role emphasizes CI/CD, testing, observability, and cross-tenant isolation.

Formación

• 5+ years of backend Python experience with async/await.
• Strong knowledge of FastAPI and PostgreSQL.
• Experience with LLM APIs and prompt engineering.

Responsabilidades

• Lead ownership of the deepagents/LangGraph runtime and safety middleware.
• Design FastAPI endpoints with async I/O and SSE streaming.
• Implement SELECT-only, injection-safe SQL across multi-tenant schemas.
• Integrate AWS Bedrock and manage LLM routing decisions.
• Instrument runs with MLflow and participate in eval framework improvements.
• Collaborate on RAG retrieval using pgvector and FAISS.

Conocimientos

Python

Async/await

English communication

Security mindset

Observability

Herramientas

FastAPI

PostgreSQL

LangGraph/LangChain

SSE streaming

AWS Bedrock

S3

pytest

CI/CD

Descripción del empleo

EPAM Systems, Inc. seeks a Lead Full-Stack, Data and AI Agent Engineer to build a production-grade agentic AI platform for upstream oil & gas operations. You will evolve the deep-agent core that translates engineers’ questions into safe, schema-aware SQL and multi-step workflows.

You will design FastAPI endpoints, ensure injection-safe SQL, and integrate AWS Bedrock with LangChain workflows. This role emphasizes CI/CD, testing, observability, and cross-tenant isolation.