> Markdown version of [/jobs/ext/1167218-back-end-engineer-python-gcp-gen-ai](https://www.wearedevelopers.com/jobs/ext/1167218-back-end-engineer-python-gcp-gen-ai). 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).

---

# Back End Engineer (Python + GCP + Gen AI)

- **Company:** First Soft Solutions
- **Location:** New York, NY, United States
- **Experience:** Expert
- **Salary:** $97,000.0 - $185,000.0
- **Contract:** Permanent contract
- **Skills:** Clean Code Principles, Java (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Audit Trail, Cloud Computing, Databases, Continuous Integration, Data Validation, Python (Programming Language), PostgreSQL, Enterprise Messaging Systems, Microsoft SQL Server, Regression Testing, Software Engineering, SQL Databases, Systems Integration, Enterprise Data Management, Data Logging, Enterprise Software Applications, Retrieval-Augmented Generation, Large Language Models, Grafana, Prompt Engineering, Rate Limiting, AngularJS, Enterprise Integration, Restful APIs, Network Server
- **Published:** July 3, 2026
- **Apply:** https://www.careerjet.com/jobad/us6435f805263d6b8e061fc80cb26e10cd

## About the Role

We are seeking an experienced AI Engineer to design and build LLM-powered automation solutions that improve operational workflows across Finance and Business Operations. This is a hands-on engineering role, focused on building reliable, scalable, and production-ready AI systems-not research., * 7+ years of software engineering experience, including 2+ years building AI/LLM-based production applications.

 * Strong hands-on expertise in Python and Java for enterprise application development.
 * Experience working with LLM APIs such as OpenAI, Claude, or similar platforms.
 * Strong understanding of:

 * Prompt Engineering
 * Function/Tool Calling
 * Structured Outputs
 * Context Management
 * Experience building AI Agents / LLM workflows, including:

 * Tool integrations
 * API orchestration
 * Multi-step workflows
 * MCP server integration
 * Strong knowledge of AI reliability and safety patterns, including:

 * Output validation
 * Hallucination mitigation
 * Cost optimization
 * Rate limiting
 * Audit logging
 * Experience integrating enterprise systems using REST APIs, SQL databases, and messaging systems.
 * Strong software engineering fundamentals:

 * Clean coding practices
 * Testing and debugging
 * CI/CD
 * Observability and monitoring
 * Excellent communication skills with the ability to explain AI capabilities to technical and non-technical stakeholders.

Preferred Qualifications

 * Experience with RAG (Retrieval-Augmented Generation) pipelines.
 * Knowledge of Vector Databases and document processing systems.
 * Familiarity with LLM evaluation frameworks, regression testing, and human review systems.
 * Experience in Financial Services, Operations, or highly regulated environments.
 * Exposure to workflow orchestration tools such as Temporal.

## Description

You will work at the intersection of Software Engineering and Applied AI, developing intelligent agents that integrate with enterprise systems, automate workflows, and deliver secure, auditable, and trustworthy outputs.
This role requires close collaboration with business and engineering teams to create impactful AI-driven solutions that support day-to-day operations. Key Responsibilities

 * Design and develop LLM-powered agents to automate business and operational workflows, including document processing, data validation, and exception handling.
 * Build integrations between AI agents and internal systems using APIs, databases, enterprise tools, and MCP servers.
 * Implement guardrails, validation frameworks, and human-in-the-loop workflows to ensure reliable and trustworthy outputs.
 * Develop production-grade AI applications with strong observability, logging, monitoring, auditability, and cost tracking.
 * Partner with stakeholders to identify automation opportunities and convert requirements into scalable AI solutions.
 * Build reusable AI engineering frameworks, including:

 * Prompt management
 * Context orchestration
 * Output validation
 * Evaluation and testing frameworks
 * Stay updated on emerging LLM technologies, tools, and APIs to recommend practical architecture and model choices.
 * Collaborate with architecture and engineering teams to ensure secure integration with enterprise platforms, authentication, and governance standards., Languages: Python, Java
LLM Platforms: Claude, OpenAI, Enterprise AI Models
Integrations: MCP Servers, REST APIs
Databases: PostgreSQL, SQL Server
Cloud/Infrastructure: AKS, Enterprise Data Platforms
DevOps: GitHub Actions, CI/CD Pipelines
Monitoring: Logging & Observability Tools Why Join Us?

 * Work on high-impact AI automation initiatives within Finance and Operations.
 * Build production-grade AI systems used by enterprise teams daily.
 * Collaborate with experienced engineering and business leaders.
 * Opportunity to contribute in a high-ownership role with a right-to-hire path., Job Description: Note: Fidelity will not provide immigration sponsorship for this position. The Role As a Senior Full Stack Developer in a Quantitative Development team, you …
 + 1 day ago, Job Description: Note: Fidelity will not provide immigration sponsorship for this position. The Role As a Senior Full Stack Developer in a Quantitative Development team, you …
 + 1 day ago
+


## Related Videos

- [Kubernetes and Microservices with Multi-Model Databases](https://www.wearedevelopers.com/videos/382-kubernetes-and-microservices-with-multi-model-databases)
- [How to Stop Choosing JavaScript Frameworks and Start Living](https://www.wearedevelopers.com/videos/118-how-to-stop-choosing-javascript-frameworks-and-start-living)
- [5 steps for running a Kubernetes environment at scale](https://www.wearedevelopers.com/videos/88-5-steps-for-running-a-kubernetes-environment-at-scale)
- [How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge](https://www.wearedevelopers.com/videos/1328-how-to-avoid-llm-pitfalls-mete-atamel-and-guillaume-laforge)
- [Coffee with Developers - Maria Apazoglou](https://www.wearedevelopers.com/videos/1209-coffee-with-developers-maria-apazoglou)
- [All your telemetry data from any source in one place](https://www.wearedevelopers.com/videos/57-all-your-telemetry-data-from-any-source-in-one-place)

## Related Articles

- [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models)
- [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)
- [Got AI ideas but no money? Here are 10 free ways to level up your AI skills with Google Cloud](https://www.wearedevelopers.com/magazine/600-got-ai-ideas-but-no-money-here-are-10-free-ways-to-level-up-your-ai-skills-with-google-cloud)
- [The Prompt Engineer ✍️](https://www.wearedevelopers.com/magazine/216-the-prompt-engineer)
- [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering)