Sr. AI Platform Engineer
Mentions experience using Vibe coding platforms as a nice-to-have; not required but preferred.
About the Role
Senior AI Platform Engineer to design and implement the generative AI layer of the NEMESIS analytics platform, enabling natural-language interaction, conversational interfaces, prompt orchestration, retrieval pipelines, and visualization-on-demand. Hands-on role embedding LLM/SLM capabilities into production systems and collaborating with product and backend teams to deliver scalable GenAI features for business users.
Job Description
Role
Senior/Lead AI Platform Engineer responsible for architecting and implementing the generative AI layer of the NEMESIS analytics platform. The role is a hands-on senior individual contributor position embedded in the product development team and focuses on enabling natural-language interaction, conversational interfaces, and production-grade GenAI features that support business users.
Key Responsibilities
- Design, develop, and implement LLM/SLM capabilities to support model interaction, scenario planning, and visualization workflows.
- Build conversational interfaces and prompt orchestration for interactions with structured data and predictive models.
- Design and implement retrieval pipelines, embeddings usage, and integrations with vector databases or agent frameworks.
- Develop APIs, microservices, and backend components to embed generative AI into NEMESIS.
- Implement visualization-on-demand driven by chat-based instructions.
- Integrate LLM outputs with Aviana’s case management system and external systems via APIs.
- Establish best practices for prompt engineering, safety, evaluation, and model lifecycle management.
- Influence architectural decisions around generative AI, data pipelines, and platform scalability.
- Mentor and elevate the team’s generative AI capabilities and contribute to roadmap planning.
Requirements
- Bachelor’s or Master’s in Computer Science or equivalent.
- US citizen or permanent resident (Green Card required).
- 5+ years of software engineering experience building production systems.
- Hands-on experience integrating LLMs (e.g., OpenAI, Anthropic, Azure OpenAI) into products or applications.
- Strong backend engineering skills (Python, Node.js, or similar).
- Experience with vector databases, embeddings, retrieval pipelines, or agent frameworks.
- Experience building APIs, microservices, and event-driven systems.
- Familiarity with predictive analytics workflows.
- Experience with at least one cloud provider: AWS, GCP, or Azure.
Nice to Have
- Experience with no-code or low-code platforms.
- Experience with data visualization libraries or BI tools.
- Experience with case management or workflow automation systems.
- Exposure to MLOps, model monitoring, or model governance.
- Experience with AI Agents or agentic AI systems.
- Experience designing and developing products and cloud-native web applications.
- Experience using Vibe coding platform(s).
Location & Work Type
- Remote (United States) with some travel as needed; hybrid remote in Yorba Linda, CA (ability to commute to Yorba Linda, CA 92887 required).
- Full-time.
Compensation
- Pay: Up to $200,000.00 per year.
Benefits
- 401(k)
- 401(k) matching
- Health insurance
- Dental insurance
- Vision insurance
- Paid time off