Gen AI Engineer

InfoDyne Solutions, LLC; Menlo Park (CA); Híbrido; USD 140.000 - 210.000; Jornada completa

Descripción de la vacante

InfoDyne Solutions, LLC is seeking a Gen AI Engineer in a hybrid role in Menlo Park to build scalable LLM-powered applications, RAG pipelines, and AI agents. You will integrate internal data, APIs, and vector stores, while delivering reliable, secure Python services.

You will work with product, data, and engineering teams to translate requirements into practical AI solutions, design evaluation frameworks, and ensure performance and safety in production systems.

Formación

• ,
• Proficient Python programming and software development.

Responsabilidades

• Design, develop, and deploy LLM-powered applications using RAG architectures, embeddings, vector databases, and prompt engineering.
• Build AI agents capable of reasoning, planning, tool usage, and multi-step task execution.
• Create evaluation frameworks, guardrails, and monitoring processes to improve model quality and safety.
• Integrate commercial and open-source LLMs with internal systems, APIs, and enterprise data.
• Develop clean, maintainable Python code and production-ready services.
• Collaborate with product, data, and engineering teams to translate requirements into effective AI solutions.
• Troubleshoot, optimize, and continuously improve application performance.

Conocimientos

Python programming

LLMs & RAG pipelines

agent frameworks & APIs

REST APIs & cloud platforms

analytical & collaboration skills

Herramientas

LangChain

LlamaIndex

Git

Descripción del empleo

Location

Menlo Park, CA

Mode

Hybrid with 3 days’ work from office.

About The Role

We are seeking a Gen AI Engineer to build intelligent, scalable applications powered by large language models (LLMs). You will develop RAG solutions, AI agents, and Python-based services that solve real-world business problems while ensuring accuracy, reliability, security, and performance.

Key Responsibilities

• Design, develop, and deploy LLM-powered applications using RAG architectures, embeddings, vector databases, and prompt engineering.
• Build AI agents capable of reasoning, planning, tool usage, and multi-step task execution.
• Create evaluation frameworks, guardrails, and monitoring processes to improve model quality and safety.
• Integrate commercial and open-source LLMs with internal systems, APIs, and enterprise data.
• Develop clean, maintainable Python code and production-ready services.
• Collaborate with product, data, and engineering teams to translate requirements into effective AI solutions.
• Troubleshoot, optimize, and continuously improve application performance.

Required Qualifications

• Strong Python programming and software development skills.
• Practical experience with LLMs, RAG pipelines, embeddings, vector stores, and prompt engineering.
• Understanding of agent frameworks, function calling, APIs, and workflow orchestration.
• Familiarity with REST APIs, databases, Git, testing, and cloud platforms.
• Strong analytical, communication, and collaboration skills.

Desired Qualifications

Experience with LangChain, LlamaIndex, model evaluation, fine-tuning, and deployment workflows.

Nice-to-Have

Knowledge of MLOps, CI/CD, containerization, observability, and responsible AI practices.