AI Engineer

Compunnel Inc.; Phoenix (AZ); Sur place; USD 120 000 - 190 000; Plein temps

Avantages offerts par ce poste

Hybrid work arrangement

Résumé du poste

Compunnel, Inc. is seeking an experienced AI Engineer to build and deploy Generative AI, Agentic AI, LLM, and RAG solutions in production. You will design scalable AI applications, select models, and justify architecture decisions based on performance and cost.

Hybrid work in Phoenix, AZ is offered. The role emphasizes strong Python engineering, backend and API development, and cloud deployment with security and governance considerations.

Qualifications

• Hands-on experience building GenAI/LLM-powered apps in production.
• Experience designing Agentic AI solutions with LangChain/LangGraph.
• Strong Python development for AI services, APIs, automation, and backends.
• Experience deploying AI solutions on GCP/AWS/Azure.

Responsabilités

• Build, deploy, and scale AI-powered applications using LLMs in production.
• Design agentic workflows including tool calling and orchestration layers.
• Implement RAG solutions with vector databases and retrieval architectures.
• Develop scalable backend services and APIs in Python.
• Evaluate model performance, cost, latency, and accuracy trade-offs.

Connaissances

GenAI

LLMs

Agentic AI

Python development

Cloud deployment

Security & governance

LLM evaluation

APIs

Low latency

Stakeholder collaboration

Outils

LangChain

LangGraph

Vector databases

Embeddings

Retrieval architectures

Public cloud platforms

Description du poste

We are seeking an experienced AI Engineer with hands-on experience building and deploying Generative AI, Agentic AI, LLM, and RAG solutions in production environments. The ideal candidate will be able to design scalable AI applications, select appropriate models and frameworks, and explain architectural decisions based on performance, cost, latency, and accuracy considerations. This role requires strong Python engineering, backend and API development, cloud deployment experience, and an understanding of security, governance, and compliance requirements. The position follows a hybrid work arrangement in Phoenix, Arizona.

Key Responsibilities

• Build, develop, and deploy AI-powered applications using LLMs in production environments.
• Design agentic workflows, tool calling, orchestration layers, reasoning chains, and multi-step AI systems using frameworks such as LangChain and LangGraph.
• Design and implement Retrieval-Augmented Generation (RAG) solutions using vector databases, embeddings, and retrieval architectures.
• Develop scalable AI services, APIs, automation platforms, and backend systems using Python.
• Evaluate, benchmark, and select appropriate AI models for specific business use cases.
• Analyze model performance, cost, latency, and accuracy trade-offs when making technology and architecture decisions.
• Develop scalable backend applications and customer-facing systems with a focus on reliability and low latency.
• Deploy and operate AI solutions within public cloud environments.
• Apply security, governance, and compliance principles when designing and implementing AI solutions.
• Collaborate with technical and business stakeholders to translate requirements into reliable AI solutions.

Required Qualifications

• Hands-on experience building and deploying GenAI and LLM-powered applications in production environments.
• Experience designing and implementing Agentic AI solutions using LangChain, LangGraph, or similar frameworks.
• Strong experience developing RAG solutions utilizing vector databases, embeddings, and retrieval architectures.
• Strong Python development experience for AI services, APIs, automation platforms, and scalable backend systems.
• Experience with LLM evaluation, benchmarking, and model selection.
• Strong understanding of model performance, cost, latency, and accuracy trade-offs.
• Experience developing scalable backend applications and APIs.
• Experience deploying and operating AI solutions on public cloud platforms such as GCP, AWS, or Azure.
• Understanding of security, governance, and compliance considerations for AI solutions.

Preferred Qualifications

• Experience working with regulated environments and security-first engineering practices.
• Experience with customer-facing AI applications.
• Experience designing low-latency, highly reliable AI and backend systems.
• Experience with multiple LLM providers, models, and AI frameworks.
• Experience with advanced agent orchestration and multi-step AI architectures.