About the role
Role Summary:
We are seeking a Generative AI Engineer to build, optimize, and scale production-ready AI applications. You will design complex multi-agent systems, implement advanced RAG pipelines, and manage the deployment of both frontier and local LLMs. The ideal candidate blends deep machine learning expertise with modern software engineering practices.
Technical Stack:
LLMs: Gemini, OpenAI, Claude, Llama, and Local Model deployment.
Frameworks: LangChain, LlamaIndex, and Hugging Face.
Orchestration: LangGraph and Multi-Agent Systems (MAS).
Development: Python, FastAPI, and Asynchronous Programming.
RAG & Data: PostgreSQL, Vector Databases, and Advanced Retrieval strategies.
ML/DL: PyTorch, TensorFlow, and Model Fine-tuning.
Deployment: Docker, Production API management, and LLM monitoring.
Tools: Prompt Engineering, Workflow Design, and GenAI Optimization.
Key Responsibilities:
- Develop and orchestrate sophisticated AI workflows using LangGraph and multi-agent architectures.
- Build and maintain Advanced RAG systems utilizing LlamaIndex and vector databases for high-accuracy retrieval.
- Integrate and swap diverse LLMs (commercial and open-source) based on performance and cost requirements.
- Design and deploy high-performance, scalable backend services using FastAPI and Async Python.
- Fine-tune large language models (LLMs) using PyTorch/TensorFlow to improve domain-specific performance.
- Optimize GenAI workflows for latency, cost, and reliability using advanced prompt engineering and monitoring tools.
- Containerize and deploy AI services via Docker to production environments.
Required Qualifications:
- Hands-on experience building and deploying GenAI applications in a production setting.
- Strong proficiency in Python and the modern AI library ecosystem (LangChain, LlamaIndex, etc.).
- Experience with vector search, embedding models, and advanced data retrieval patterns.
- Knowledge of model fine-tuning techniques and local LLM quantization/hosting.
- Familiarity with production-grade monitoring, API security, and CI/CD for ML.
Compensation, Benefits and Duration
Medical, vision, and dental benefits, 401k retirement plan, variable pay/incentives, paid time off, and paid holidays are available for full time employees.
This position is not available for independent contractors.
No applications will be considered if received more than 120 days after the date of this post.
Millions of jobs, with real people getting hired every day
Questions, answered
Click "Apply with JobAssist" – we tailor your resume and application to this role and submit it for your approval.
Yes. This role at Photon Career Site was screened before publishing – we confirmed the employer before listing it.
The employer didn't disclose a salary range for this listing. JobAssist shows pay whenever it's available.
This position can be done from anywhere, with no in-office requirement.
Yes – every application is tailored from your profile and this job's requirements, and you can review and edit before it's sent.