Skip to main content

Senior Full Stack Engineer with LLM (Python, React, Cloud)

Tecnología
EPAM Systems
Desde Casa, ArgentinaHace 1 mesesHasta 18/5/2026
Presencial

Descripción del puesto

We are seeking a Senior Full Stack Engineer with expertise in LLMs and cloud technologies to design, implement, and lead the development of cutting-edge AI applications, platforms, and tools that drive measurable customer value.

  • *Responsibilities
  • Design and implement full-stack applications, AI agents, and platform components to accelerate GenAI agent development, validation, and deployment
  • Build developer tooling, CI/CD pipelines, and observability measures for fast and secure iteration, including evals, rollouts, and telemetry
  • Apply secure SDLC and privacy-by-design principles, including threat modeling and least privilege practices
  • Collaborate with product managers, UX designers, and domain experts to deliver impactful customer-focused solutions
  • Utilize advanced LLM patterns such as RAG, routing, tool-use, and retrieval to optimize AI systems for reliability, cost efficiency, and trust metrics
  • Lead architecture planning, mentor team members, and take ownership of large, complex projects
  • Deliver innovative solutions that ensure safe, reliable, and cloud-native systems are deployed to production
  • *Requirements
  • 3+ years of professional software engineering experience
  • Background in full-stack development combined with cloud expertise in AWS, Azure or GCP
  • Expertise in AI agent development, backend systems, and frontend development
  • Knowledge of CI/CD processes, Infrastructure as Code, site reliability engineering and secure SDLC practices
  • Proven competency in delivering production-grade cloud-based systems with high security and reliability
  • Strong problem-solving ability, ownership mindset, and cross-functional communication skills
  • Upper-Intermediate English language proficiency (B2)
  • *Nice to have**
  • Background in delivering software products independently or in fast-paced environments
  • Expertise in taking AI agents from concept to production with A/B testing, safety evaluations, and continuous improvement
  • Familiarity with LangChain, LangGraph, MCP, vector/RAG systems, and OpenSearch technologies
  • Understanding of LLM mechanics, failure modes, fine-tuning, and model adaptation
  • Knowledge of regulatory frameworks like SOC 2 and HIPAA
Keywords
large-language-model-llmpythonreact-jsreactplanning-and-designvisual-art-designproduct-development-and-designartificial-intelligencegenerative-artificial-intelligence-generative-aitraining-and-developmentcustomer-intelligence-cicontinuous-integrationcd-certificate-of-depositci-cdobservabilityiterationsoftware-development-lifecyclesystems-development-life-cycle-sdlcleast-privilegepolicies-and-practicesuser-experience-uxmobile-app-user-experiencecustomer-centricityretrieval-augmented-generation-ragrouting-and-switchingsearch-and-retrievalcost-efficiencytrust-metricsplanning-and-forecastingelectrical-engineering-and-planningmentoringamazon-web-servicesmicrosoft-azuregoogle-cloud-platformgood-clinical-practice-gcpfront-end-developmentinfrastructure-as-code-iacsite-reliability-engineering-srecompetenciesa-b-testingtesting-and-analysisenvironment-health-and-safety-hssecontinuous-improvement-process-ciplangchainlanggraphmicrosoft-certificationmodel-context-protocol-mcpopensearchfine-tuningvehicle-modification-tuningservice-organization-controls-socsecurity-operations-center-socsystem-on-a-chip-socsoc-2soc-ii-compliancehipaa-compliancehealth-information-privacy-hipaa

¿Te interesa este puesto?