> Markdown version of [/jobs/ext/4361319-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4361319-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI Engineer

- **Company:** Ponchos & Huaraches, Inc.
- **Location:** United States (Remote available)
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Amazon S3, Cloud Computing, Databases, Customer Data Management, Decision Support Systems, Python (Programming Language), PostgreSQL, Liquibase, Machine Learning, Rapid Prototyping Process, OpenAI, Search Technologies, Software Engineering, SQLAlchemy, Systems Integration, Enterprise Data Management, Enterprise Software Applications, Retrieval-Augmented Generation, Large Language Models, Claude Code, Multi-Agent Systems, Prompt Engineering, State Machines, Backend, Agentic-AI, Fastapi, AWS Glue, Machine Learning Operations, Evaluation of Large Language Models, Amazon Simple Queue Service (SQS), Terraform, Automation Anywhere
- **Published:** October 5, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=16e51f89dac07240

## About the Role

* 3-7+ years of experience in software engineering, applied AI, or ML systems.
 * Experience building or integrating LLM-powered applications.
 * Strong skills in prompt engineering and structured output design.
 * Familiarity with RAG systems, embeddings, and vector databases.
 * Proficiency in Python and experience building APIs or backend services.
 * Comfort working in fast-moving, collaborative environments., * Experience designing multi-agent workflows.
 * LLM evaluation and testing frameworks.
 * Enterprise system integrations.
 * Startup or high-growth company experience., * Engineers who enjoy building and iterating.
 * Problem-solvers who connect technical design to business outcomes.
 * Collaborative builders who are excited about applying AI in real enterprise environments.
 * If you're excited about designing intelligent systems that directly impact customer workflows, we'd love to talk.

## Description

As an AI Engineer, you will join a dedicated product pod aligned to one of Harpin's product families:

 * Clarity - Delivers trusted, board ready insights to complex business questions through extreme diagnosis
 * Concierge - Empowers frontline staff with autonomous decision support to drive superior CX & personalization
 * Canon - Trusted data + our agentic intelligence creates a secure foundation for every decision and interaction

You'll work closely with Product Managers and engineers to design, prototype, and scale AI-native capabilities embedded directly into enterprise workflows.

Our Current AI Stack

 * Backend Framework: FastAPI (Python) with Uvicorn ASGI server
 * AI/LLM: Multi-provider - OpenAI, Anthropic, Google - routed through a Portkey gateway (containerized)
 * Orchestration: LangGraph (state machine workflows)
 * Data/Query Engine: AWS Athena + AWS Glue (catalog)
 * Database: PostgreSQL 14.5 (with SQLAlchemy ORM, Liquibase migrations)
 * Cloud Infrastructure: AWS (S3, SQS, Athena, Glue, Cognito for auth) - managed via Terraform For daily use, we use claude code, codex and cline heavily
*, * Translate business objectives into AI-powered workflows.

 * Build LLM-driven features grounded in real enterprise data.
 * Integrate advanced proprietary machine learning AI models to augment capabilities in our products
 * Develop evaluation methods to measure quality, reliability, and business impact.
 * Apply Agentic & Autonomous Development Techniques.
 * Design and implement multi-step AI workflows (retrieval, reasoning, tool use).
 * Use AI-assisted development to accelerate iteration and experimentation.
 * Implement guardrails and structured outputs to ensure enterprise-grade reliability.

Engineer Context & Data Grounding

 * Build structured context pipelines using normalized enterprise data, embeddings, and vector search.
 * Design systems that maintain workflow state and continuity.
 * Ensure AI outputs are explainable, auditable, and aligned with customer data realities.

Rapid Prototyping & Iteration

 * Contribute to early-stage prototypes during customer engagements.
 * Iterate quickly based on real-world feedback from contact centers and marketing operations teams.
 * Help convert successful prototypes into scalable product capabilities.

Platform & Systems Integration

 * Develop backend services and APIs that support AI orchestration.
 * Work within cloud-native environments to ensure performance, reliability, and security.
 * Collaborate across product pods to share reusable AI components and patterns., * Engineers are empowered to design outcomes, not just implement requirements.
 * Customers experience working solutions earlier in the engagement cycle.
 * Feedback loops are fast and collaborative.
 * AI tools are leveraged thoughtfully to improve speed and quality.
 * We are building systems that operate inside real enterprise workflows where reliability, data grounding, and measurable impact matter.