Build production-grade LLM systems across RAG pipelines, agents, and document intelligence.

- Experience Level: 2-4 years
- Core Stack: AWS Bedrock, Llama Index, Lang Chain, Vector Databases, Python

About Brand & Bot

Brand & Bot is a digital modernization and AI company that helps organizations transform their revenue engine by connecting brand, data, automation, and AI into one unified operating system. We build production-grade AI systems that go beyond chatbots, specializing in document intelligence, retrieval-augmented generation (RAG), AI agents, and end-to-end LLM pipelines integrated into real products. Our focus is on building AI systems that are maintainable, explainable, and designed to scale.

The Role

We are looking for an AI Developer with hands-on experience building and deploying LLM-based systems in production environments. You will work on real-world AI pipelines involving raw document parsing and ingestion, intelligent chunking and retrieval, vector search and RAG architectures, AI agents and tool-calling workflows, and prompt engineering and role is adecuado for someone who enjoys transforming unstructured data and documents into reliable, production-ready AI systems.

What You Will Do

Core Responsibilities

- Design and build LLM-based applications using modern AI frameworks (Llama Index, Lang Chain)
- Implement end-to-end RAG pipelines from data ingestion to retrieval and generation
- Build and maintain vector-based retrieval systems using production databases like Qdrant, Pinecone, FAISS, Weaviate, and Chroma
- Design and optimize document ingestion pipelines (PDFs, DOCX, complex layouts, tables)
- Define intelligent chunking strategies that preserve semantic context
- Create metadata extraction and enrichment workflows

AI Agents and Tool Integration

- Build AI agents capable of multi-step reasoning, planning, and context management
- Design and implement custom tools for agents, including API integrations, database queries, and document retrieval
- Orchestrate agentic workflows using Lang Chain and Llama Index patterns

LLM Integration and Deployment





- Implement tool-calling and function definitions for agents

Production and Collaboration

- Collaborate with backend and product teams to integrate AI into production environments
- Optimize AI pipelines for latency, cost, accuracy, and reliability
- Implement observability and monitoring for LLM applications
- Contribute to documentation, internal tooling, and applied AI best practices
- Participate in model evaluation and continuous improvement workflows

What You Will Need to Be Successful

Required Experience

- 2-4 years of professional experience in AI, ML, or applied LLM development
- Strong proficiency in Python and AI development workflows

Technical Skills - Core Frameworks

- Deep experience with Llama Index (indexing, querying, advanced retrieval patterns)
- Deep experience with Lang Chain (chains, agents, tools, LLM integrations)
- RAG architectures (retrieval, ranking, generation, hybrid search)
- AI agents (ReAct, function calling, multi-step reasoning)
- Tool design and integration for agent workflows

Technical Skills - Vector Databases

- Hands-on experience with at least one: Qdrant, Pinecone, FAISS, Weaviate, Chroma
- Understanding of vector search optimization and hybrid search (dense + sparse)
- Metadata filtering and indexing strategies

Technical Skills - Document and LLM Engineering

- Hands-on experience with raw document parsing (PDFs, DOCX, complex layouts, tables)
- Prompt engineering and design patterns
- Embedding models and similarity search optimization

Technical Skills - Cloud and Production

- Familiarity with AWS ecosystem (Bedrock, S3, Lambda, SQS)
- Model evaluation, A/B testing, and iteration workflows




- Observability and monitoring for LLM applications
- API design and integration patterns

Soft Skills

- Comfortable working in a consulting or client-facing environment
- Strong communication skills to explain AI trade-offs and technical decisions clearly
- English required (professional/working level)
- Self-driven with a focus on ownership and reliability

Nice to Have

- Experience with fine-tuning open-source models
- Familiarity with LLMOps tools (Lang Smith, Weights and Biases, MLflow)
- Knowledge of structured output generation and validation
- Experience with streaming responses and real-time applications
- Understanding of cost optimization strategies for LLM applications
- Background in NLP or information retrieval

How We Work

- Remote-first and async-friendly culture
- Contractor-based engagements (hourly or project-based)
- Emphasis on clarity, ownership, and production quality
- Pragmatic, production-focused approach to AI - we ship real systems
- Close collaboration across engineering, product, and delivery teams
- Regular knowledge sharing and technical discussions

What Sets This Role Apart

- Work on real production AI systems, not just prototypes or demos
- Build intelligent agents that solve complex, multi-step problems
- Direct impact on client outcomes and measurable business value
- Exposure to diverse industries and challenging use cases
- Opportunity to shape AI best practices and tooling within a growing company
- Learn from and collaborate with experienced AI practitioners
- Work with cutting-edge AI technologies before they become mainstream

The Tech Stack You Will Use

Frameworks and Libraries

- Hugging Face Transformers

Vector Databases

Cloud and Infrastructure

Development Tools

- Git, Git Hub or Git Lab

Observability

- Lang Smith, Cloud Watch
- Custom logging and monitoring solutions

Role snapshot

Location Remote (Chile)

Engagement Contract

Category AI & ML

Experience 2-4 years

Cloud AWS Bedrock, Llama Index, Lang Chain, Vector Databases, Python

#J-18808-Ljbffr

📌 AI Developer (Chile)
🏢 Brand & Bot
📍 Chile