Lead Full-Stack, Data and AI Agent Engineer

EPAM Systems, Inc.; Colombia; A distancia; COP 400.080.000 - 633.460.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare benefits

Paid time off and sick leave

Upskilling and certification courses

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 agent platform for upstream oil & gas operations. You will evolve the core that converts engineers’ questions into safe, schema-aware SQL and multi-step workflows.

You’ll lead the deepagents/LangGraph runtime, design FastAPI endpoints, ensure injection-safe SQL, and integrate Bedrock with LangChain for scalable AI services.

Formación

• Proven backend engineer with 5+ years in Python and async programming.
• Strong experience with FastAPI or similar frameworks.
• Hands-on experience with AWS core services (Bedrock, RDS, S3) and no hardcoded credentials.
• Deep knowledge of SQL/PostgreSQL, including safe, injection-resistant SQL generation.
• Familiarity with LangGraph/LangChain or similar agent orchestration tools.
• Solid understanding of LLM APIs (Bedrock, OpenAI, Anthropic) and prompt engineering.
• CI/CD and testing discipline (lint/format gates, pytest, GitHub Actions).
• Security-first mindset: tenant isolation and cross-tenant leakage prevention.
• Observability mindset using MLflow or equivalent to measure quality, latency, and tokens.
• Ability to learn oil & gas terminology (ESP, gas lift, decline curves).
• Excellent client communication in English; Spanish is a plus.

Responsabilidades

• Lead ownership of the deepagents/LangGraph runtime, extending agent tools and safety middleware.
• Design FastAPI endpoints with async I/O and SSE streaming for real-time responses.
• Implement SELECT-only, injection-safe SQL across per-tenant schemas.
• Integrate AWS Bedrock and manage LLM routing decisions.
• Instrument agent runs with MLflow and contribute to eval framework improvements.
• Collaborate on RAG retrieval using pgvector, FAISS, and S3-backed storage.

Conocimientos

Python

Async/Await

FastAPI

PostgreSQL

SQL Security

LangChain

LangGraph

AWS Bedrock

CI/CD

pytest

Tenant Isolation

LLM APIs

Observability

SSE Streaming

Redis

Herramientas

AWS Bedrock

pgvector

FAISS

S3

LangGraph

LangChain

uv

ruff

pytest

Redis

APScheduler

Descripción del empleo

We are looking for a Lead Full-Stack, Data and AI Agent Engineer to build a production-grade agentic AI platform for upstream oil & gas operations (ESP, gas lift, plunger lift, chemical injection). As a Lead Full-Stack, Data and AI Agent Engineer, you will evolve the deep-agent core that converts petroleum engineers’ natural-language questions into safe, schema-aware SQL and multi-step reasoning workflows, and help the team ship reliably.ResponsibilitiesLead ownership of the deepagents/LangGraph agent runtime, extending agent tools, subagents, and safety middlewareDesign FastAPI endpoints using async I/O (asyncpg/psycopg3) and SSE streaming to deliver real-time agent responsesImplement SELECT-only, injection-safe SQL generation across per-tenant PostgreSQL schemasIntegrate AWS Bedrock (Claude via langchain-aws) and manage LLM factory/model routing decisionsInstrument agent runs with MLflow and contribute improvements to the eval frameworkCollaborate on RAG retrieval using pgvector, FAISS, and S3-backed document storageRequirementsProven track record with 5+ years of backend engineering in Python, including strong async/await skills and FastAPI or a comparable frameworkHands-on experience with AWS core services such as Bedrock, RDS, and S3, following a strict no-hardcoded-credentials approachPractical experience using LangGraph, LangChain, or a similar agent-orchestration frameworkSolid SQL/PostgreSQL experience, with confidence owning safety-critical code such as SQL injection prevention and tenant isolationDeep understanding of LLM APIs (Bedrock, OpenAI, Anthropic) and prompt engineering techniquesStrong CI/CD and testing discipline, including lint/format gates, pytest/Jest, and GitHub ActionsSecurity-first mindset for tenant isolation, including tenant isolation, SELECT-only SQL, and no cross-tenant leakageObservability and eval mindset using MLflow or equivalent, measuring quality, latency, and tokens before shippingAbility to learn oil & gas / production-ops terminology (ESP, gas lift, decline curves) even without prior backgroundEnglish proficiency for client-facing communication; Spanish is a nice-to-haveNice to haveWorking knowledge of TypeScript/React/Next.js, including SSE event formats, content types, and payload shapes for cross-stack debuggingFamiliarity with uv, Ruff, and pytest workflowsExperience with MLflowFamiliarity with Redis/APSchedulerBackground in oil & gas domain knowledgeWe offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedInEPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.