Senior IA Engineer (Python + AWS)

GlobalLogic; Colombia; Presencial; COP 120.000.000 - 180.000.000; Jornada completa

Descripción de la vacante

GlobalLogic is seeking an experienced AI engineer to design and ship agentic systems using Python, LangGraph, LangChain, and AWS Bedrock. You will build scalable, production‑ready pipelines and ensure robust integration with data platforms like Snowflake and OpenSearch.

You will implement MCP patterns, expose services via FastAPI, and collaborate with cross‑functional teams to translate business needs into resilient agent architectures.

Formación

• Hands-on experience building agentic AI systems.
• Proficient in Python and production‑grade code.
• Experience integrating LLMs via major APIs.
• Experience with data platform integrations.

Responsabilidades

• Build multi-agent pipelines with routing, evaluation loops, retry mechanisms, and agent specialization.
• Develop with LangChain for prompt pipelines, tool-augmented agents, memory constructs, and retrieval-augmented generation workflows.
• Integrate agents with client Cloud Analytics, Snowflake, Apache Iceberg, OpenSearch via MCP and API patterns.
• Deploy on AWS Bedrock to host and manage LLM-powered agents at scale with security and cost considerations.
• Build lightweight, production-ready FastAPI services to expose agentic capabilities and instrument usage signals.
• Collaborate with Customer Success, Sales, and Analytics to translate business needs into architectures.

Conocimientos

Python

LLM integration

Agentic frameworks

LangGraph

LangChain

AgentCore

AWS Bedrock

Herramientas

Snowflake

Apache Iceberg

OpenSearch

API Gateway

Lambda

Descripción del empleo

The ideal candidate will have hands‑on experience building and shipping agentic AI systems,

with deep proficiency in Python and the modern AI engineering stack:

• Python Expertise: Python is your primary language. You write clean, production‑grade code, build robust data pipelines, and are comfortable owning the full lifecycle from
• Agentic Frameworks: Practical experience with LangGraph, LangChain, AgentCore, or comparable multi‑agent orchestration frameworks - including agent routing, state management, tool use, memory, and evaluation.
• LLM Integration: Demonstrated experience integrating large language models via AWS Bedrock, Anthropic APIs, or similar - including prompt engineering, context management, and output validation.
• Data Source Integrations: Hands‑on experience connecting applications to modern data platforms including Snowflake, Apache Iceberg, OpenSearch, or similar.
• MCP / Tool‑Use Patterns: Familiarity with Model Context Protocol (MCP) or equivalent patterns for giving agents structured, governed access to external data systems.
• Cloud Platforms: Hands‑on AWS experience, with Bedrock exposure strongly preferred. Familiarity with IAM, Lambda, and API Gateway a plus.

Job Responsibilitie

sHere's how you'll be making an impact

• Build Multi‑Agent Pipelines: Design and implement orchestrated multi‑agent system susing LangGraph and AgentCore, including routing logic, evaluation loops, retr ymechanisms, and agent specialization patterns
• Develop with LangChain: Leverage LangChain to build sophisticated prompt pipelines ,tool‑augmented agents, memory constructs, and retrieval‑augmented generatio nworkflows
• Integrate Across the Data Ecosystem: Build reliable, performant Python integration sconnecting agents to client Cloud Analytics, Snowflake, Apach eIceberg, OpenSearch, and other data sources via MCP and direct API patterns
• Deploy on AWS Bedrock: Leverage AWS Bedrock to host, invoke, and manag eLLM‑powered agents at scale, ensuring reliability, cost efficiency, and securit ycompliance
• Build FastAPI Services: Develop lightweight, production‑ready API services tha texpose agentic capabilities to downstream consumers and orchestration platforms ,instrument your work, and evolve solutions based on real usage signals
• Collaborate Cross‑Functionally: Partner closely with Customer Success, Sales, an dAnalytics stakeholders to translate business requirements into agentic architectures