GenAI Solutions Engineer, (LLM, AI, Full stack SME)

GenAI Solutions Engineer, (LLM, AI, Full stack SME)

San Francisco, Bay Area, CA

Duration: Six months may extend to 12 months

Must be in the Greater Bay area – or in California

Domain: utilities

MUST be a US Citizen or GC holder

Translating AI capabilities into business value requires a technically versatile engineer who can bridge the gap between complex AI models and practical applications. This implementation-oriented full-stack role combines software engineering expertise with specialized knowledge of how to efficiently leverage data sources, LLMs, and AI agents in production environments to deliver tangible business value.

Accelerates user adoption through intuitive interfaces and seamless system integrations

Creates efficient data pipelines connecting LLMs to relevant utility information sources

Enables intelligent automation through multi-agent systems for complex workflows

Develops sustainable solutions that can evolve with business needs and technology advances

Key Responsibilities:

Build proof-of-concept applications and production-ready interfaces for GenAI capabilities

Connect AI services with enterprise systems (SAP, internal databases) for data exchange

Design and implement multi-agent architectures to solve complex business processes

Develop tool integration frameworks allowing AI to interact with utility systems

Create robust memory and reasoning systems for contextual, multi-step AI interactions

Implement appropriate guardrails and safety measures for AI agent systems

Gather requirements and translate business needs into technical implementation

Produce documentation and knowledge transfer materials for sustainable solutions

Expected Skillset:

Full-Stack Development : Modern front-end frameworks, back-end technologies, API design

System Integration : Experience connecting disparate systems, data orchestration, authentication

AI Application Patterns : RAG architectures, prompt engineering, agent orchestration frameworks

Agent Architecture : Knowledge of multi-agent systems, collaboration protocols, tool integration

Reasoning & Memory : Understanding of chain-of-thought reasoning, context management, planning algorithms

User Experience : Ability to design intuitive AI interfaces with appropriate feedback mechanisms

Rapid Prototyping : Demonstrated ability to quickly build working demos and iterate based on feedback