Generative AI Engineer (LLM Expert)
Location: Remote
Employment Type: Part Time / Contract
About BigRio
BigRio is a Boston-based, remote-first technology consulting firm specializing in advanced data and software solutions. We partner with forward-thinking organizations to deliver scalable, cost-effective, and innovative technology, with particular expertise in AI/ML, data engineering, and cloud-native applications. Our clients span healthcare, life sciences, government, and enterprise sectors, and we are known for our ability to tackle complex challenges with cutting-edge solutions.
About The Role
BigRio is seeking a highly skilled Generative AI Engineer with expert-level experience in LLMs, OpenAI APIs, prompt engineering, and retrieval-augmented generation (RAG). This is a senior, hands-on role—ideal for someone who has already mastered these technologies and is ready to deliver production-ready solutions. This is not a learning-on-the-job position. You will work with our internal team and clients to design, build, and optimize AI-powered applications with high-performance standards and robust infrastructure integration.
Key Responsibilities
- Design and implement LLM-driven features using OpenAI API (including reasoning vs. non-reasoning models, model versioning, temperature settings, and best practices).
- Apply advanced prompt engineering and model tuning techniques to drive performance and accuracy.
- Build retrieval-augmented generation (RAG) systems using Langchain and ChromaDB.
- Develop interactive AI tools and UIs using Gradio.
- Ensure seamless SSO integration and secure access controls.
- Implement Dockerized environments for scalable deployments.
- Connect and automate data pipelines including Google Drive integration.
- Write clean, maintainable code in Python, and contribute to a collaborative, agile development environment.
Required Qualifications
- 3-5+ years of experience in AI/ML development, with proven, expert-level hands-on work in LLMs and Generative AI.
- Mastery of the OpenAI API, including reasoning capabilities, temperature control, and fine-tuning parameters.
- Deep experience with prompt engineering and AI response optimization.
- Strong Python development skills.
- Production-level experience with Langchain, ChromaDB, and RAG architectures.
- Proficiency with Gradio for front-end prototyping.
- Experience with Docker, SSO, and cloud API integrations (e.g., Google Drive).
- Strong problem-solving and communication skills.
- Comfortable working independently and collaborating across time zones.
Nice to Have
- Experience with other vector databases and frameworks.
- Familiarity with MLOps or AI infrastructure tooling.
- Previous experience in healthcare, biotech, or highly regulated domains.
Seniority level: Entry level
Employment type: Contract
Job function: IT Services and IT Consulting
Referrals increase your chances of interviewing at Saviance by 2x
Salary: USD 72000 - 108000 per year
Experience: 5 years required