> Markdown version of [/jobs/ext/4625648-1609-senior-ai-engineer-full-stack](https://www.wearedevelopers.com/jobs/ext/4625648-1609-senior-ai-engineer-full-stack). 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).

---

# (1609) Senior AI Engineer (Full Stack)

- **Company:** Nortal LLC
- **Location:** United States (Remote available)
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** AI Evaluation, Artificial Intelligence, Amazon Web Services, Software Applications, Microsoft Azure, BigQuery, Cloud Computing, Computer Programming, Databases, Information Engineering, Information Leak Prevention, Extract Transform Load (ETL), Data Transformation, Data Retention, Distributed Systems, Python (Programming Language), Machine Learning, Performance Tuning, Salesforce.Com, SAP (Applications), Search Technologies, Software Deployment, Software Engineering, Enterprise Data Management, Pinecone, Retrieval-Augmented Generation, Large Language Models, Hallucination Detection, Llamaindex, Backend, Agentic-AI, Pgvector, Low Latency, Machine Learning Operations, Asynchronous Programming, Api Design, Entity Resolution, Data Pipelines, Microservices
- **Published:** November 7, 2026
- **Apply:** https://arc.dev/remote-jobs/j/redirect/px8f8p0o8h

## About the Role

* 5-7+ years of Software Engineering Experience: Strong foundation in backend development, distributed systems, asynchronous programming, API design, microservices, and database managemnt.
 * 2+ years of Production AI / LLM Experience: Hands-on experience designing, developing, and deploying AI-powered applications using LLM APIs, RAG pipelines, and agentic workflows in production environments.
 * 3+ years of Data Engineering & ETL Experience: Proven experience building data pipelines and integrating enterprise systems, including CRM, ERP, CPQ, or marketing platforms. Strong knowledge of data transformation, entity resolution, schema design, and data quality.
 * 3+ years of Python or Equivalent Backend Development: Strong programming skills with the ability to independently develop, integrate, and maintain production-grade AI applications.
 * 1-2+ years of Vector Database & AI Memory Experience: Practical experience with Pinecone, Pgvector, or equivalent technologies for semantic search, contextual retrieval, and persistent AI memory.
 * 1-2+ years of AI Frameworks & Orchestration: Hands-on experience using LangChain, LlamaIndex, or equivalent frameworks to develop RAG systems and agentic AI workflows.
 * 1+ year of AI Evaluation & Safety Experience: Knowledge of AI evaluation pipelines, hallucination detection, prompt injection mitigation, data leakage prevention, and model safety guardrails.
 * 1+ year of AI Performance Optimization: Experience implementing semantic caching, intelligent model routing, inference cost optimization, and latency reduction strategies.
 * 2+ years of Cloud Experience: Hands-on experience deploying and maintaining applications using AWS, Azure, or GCP.
 * 2+ years of Stakeholder-Facing Technical Delivery: Experience collaborating with business and engineering teams to identify requirements, develop solutions, and support production adoption.

Global Impact, Local Culture

## Description

* Ship End-to-End AI Products: Transform ambiguous business challenges into functional, scalable, and high-performing AI features, applications, and standalone tools.
 * Build Persistent & Compliant Memory: Design and implement AI memory architectures and vector stores (such as Pinecone and Pgvector) that preserve contextual information while ensuring compliance with data retention, privacy, and deletion policies.
 * Unify Fragmented Enterprise Data: Develop data pipelines and entity-resolution logic to integrate information across CRM, ERP, CPQ, and marketing platforms (such as Salesforce, SAP, and BigQuery), creating reliable, unified data sources that AI agents can leverage.
 * Identify High-Value Use Cases: Collaborate directly with business units to understand workflows, identify opportunities for AI-driven improvements, and prioritize use cases that demonstrate measurable value.
 * Drive Adoption: Partner with stakeholders throughout development and implementation, ensuring solutions address business needs and are successfully adopted by end users.
 * Close the Feedback Loop: Gather and communicate insights from real-world deployments to help engineering and platform teams understand model performance, limitations, and opportunities for improvement.
 * Implement EvalOps & Safety Guardrails: Build continuous evaluation pipelines to assess AI models for hallucinations, prompt injections, data leakage, and performance regressions before production deployment.
 * Optimize Cost & Latency: Implement semantic caching, intelligent model routing, and inference optimization strategies to reduce response times and operational costs while maintaining solution quality.