Backend Engineer (AI Agentic) 1904/1905

In All Media Inc; Brasil; On-site; BRL 366,300 - 470,957; Full time

Job summary

A Managed Nearshore Teams provider is seeking a Remote Backend Engineer (AI Agentic) to support high-impact AI projects. This role involves designing complex AI agents and optimizing backend architectures using Python. Candidates should have deep expertise in frameworks like LangChain and experience with vector databases such as Pinecone. Strong communication skills in English and a collaborative mindset are essential. This position allows you to engage in innovative AI challenges while working closely with diverse teams across LATAM.

Qualifications

• 3+ years of experience with AI frameworks like LangChain or LangGraph.
• 6+ years of senior-level proficiency in Python for robust API development.
• Proven experience with vector databases like Pinecone or Weaviate.

Responsibilities

• Design and implement complex AI agents and workflows.
• Build scalable high-performance backend services using Python.
• Develop Retrieval-Augmented Generation (RAG) pipelines.

Skills

LangChain

LangGraph

Python

Pinecone

Weaviate

Retrieval-Augmented Generation (RAG)

Team player

Fluent English

Tools

Kubernetes

Docker

Pandas

Spark

Job description

Position: Backend Engineer (AI Agentic)

Location: Remote from LATAM

Contract Type: Full-time Contractor

Time Zone Alignment: CT

About In All Media

We are a Managed Nearshore Teams provider headquartered in Austin, specializing in building and embedding high-performing software development teams. From design to deployment, we deliver customized solutions by connecting global talent with innovative client projects. Our model allows you to work on international challenges, collaborate with diverse teams, and grow your career while being part of a company that values expertise, creativity, and impact.

Project Overview

In this role, you will be at the forefront of the AI revolution, supporting a high-impact project focused on autonomous agents and intelligent backend architectures. You will join a collaborative, fast-paced team dedicated to building the next generation of AI-driven solutions. The project involves architecting sophisticated agentic workflows and leveraging advanced retrieval techniques to power business intelligence at scale. As a Backend Engineer (AI Agentic), you will be instrumental in transforming raw data and LLM capabilities into reliable, goal-oriented AI systems.

Key Responsibilities

• Agentic Development: Design and implement complex AI agents and multi-agent workflows using frameworks like LangChain or LangGraph.
• Backend Architecture: Build and maintain scalable, high-performance backend services using Python to support AI-driven features.
• RAG Implementation: Develop and optimize Retrieval-Augmented Generation (RAG) pipelines to provide agents with accurate, context-aware information.
• Vector Database Management: Architect and manage vector storage solutions (Pinecone, Weaviate) to ensure efficient similarity search and data retrieval.
• System Integration: Integrate Large Language Models (LLMs) with existing APIs and third-party services to enhance agent capabilities.
• Agile Collaboration: Work closely with product owners, data scientists, and fellow engineers to translate ambitious AI requirements into production-ready code.

Must-Have Skills

• AI Frameworks: Deep expertise in LangChain, LangGraph, or Semantic Kernel. ( 3 + YEARS OF EXPERIENCE)
• Backend Mastery: Senior-level proficiency in Python ( 6 + YEARS OF EXPERIENCE) and its ecosystem for building robust APIs.
• Vector Databases: Proven experience working with Pinecone, Weaviate, or similar vector search engines.
• AI Specialization: Strong understanding of Retrieval-Augmented Generation (RAG) and agentic design patterns.
• Soft Skills: A truly collaborative team player mindset with an appetite for solving ambiguous, cutting-edge problems.
• Fluent English: Excellent verbal and written communication skills for daily technical collaboration and documentation.

Nice-to-Have Skills

• Cloud & Orchestration: Experience deploying AI workloads on Kubernetes or Docker.
• Prompt Engineering: Knowledge of advanced prompting techniques and LLM fine-tuning.
• Data Engineering: Familiarity with data processing libraries like Pandas or Spark.
• Monitoring: Experience with tools for monitoring LLM performance and cost (e.g., LangSmith).

Time Zone & Collaboration

This role is 100% remote from LATAM and requires consistent overlap with teams in Central Time (CT). Flexibility is expected to accommodate key ceremonies, stand-ups, and collaborative sessions within standard Austin business hours.

Language

All interviews, documentation, and daily communication are in English.

#LI