We are looking for a hybrid AI Platform Engineer to lead the design of high-performance prompts and the development of custom AI agents and integrations across our internal platforms. Collaborating closely with our AI Platform Manager and functional business units, this role bridges the creative precision of prompt engineering with the technical fluency required to build and deploy powerful LLM-based tools using APIs, system integrations, and emerging AI infrastructure.

Prompt Engineering & Optimization

Design, test, and refine prompts for general and use-case-specific applications.

Evaluate and improve LLM output quality based on accuracy, latency, hallucination, and user satisfaction.

Maintain a scalable prompt library with robust documentation and experimentation tracking.

Custom Agent & GPT Development

Build and maintain custom GPTs (via OpenAI) or Google Agents (Gemini, Vertex AI).

Configure tools, memory, system prompts, and API-calling capabilities for agent workflows.

Ensure agents follow internal data governance and compliance policies.

API & Platform Integration

Integrate LLM functionality into internal systems (e.g., dashboards, Slack, CRMs, internal portals).

Work with APIs from OpenAI, Google Cloud, Azure, and others to create functional pipelines.

Support rapid prototyping and deployment of AI features in close coordination with product and automation teams.

Evaluation & Instrumentation

Define key performance metrics (quality, reliability, usage patterns).

Collaborate with data engineering to log, analyze, and visualize LLM performance.

Implement feedback loops to continuously optimize prompt and agent behavior.

Enablement & Documentation

Provide tooling and guidance to business users and product teams for prompt-based workflows.

Contribute to internal AI playbooks and best practices around prompt usage and API integration.

1 -3 years of experience in AI/ML, NLP applications, or full-stack product development

Hands-on experience with OpenAI APIs, Google Cloud Vertex/Gemini, or similar platforms

Strong experience with prompt engineering and LLM evaluation methods

Proficiency in Python and working with APIs, JSON, and vector databases

Familiarity with LangChain, LlamaIndex, or custom agent frameworks

Excellent collaboration and communication skills