AI Engineer only W2

AI Engineer

Location: Sunrise Florida (Hybrid - Need Local Candidates)

Focus: End-to-end solution integration and technical quality

• Owns the integrated Gen AI solution pipeline stitching together modules built by AI Engineers into a coherent functioning system across the full flow
• Designs and implements end-to-end workflow orchestration using frameworks such as LangChain LlamaIndex LangGraph AutoGen CrewAI or custom pipelines ensuring correct data flow state management error handling and fallback logic across all modules
• Owns the agentic system design at an implementation level including LLM routing tool routing logic context management multi-agent coordination patterns and guardrail integration
• Manages the full prompt & context engineering lifecycle at system level including prompt library architecture versioning templating variable injection and systematic evaluation of prompt variants across the integrated pipeline
• Implements output reliability mechanisms across the pipeline including structured output enforcement JSON/schema validation retry logic self-consistency checks and model output grounding
• Identifies and resolves cross-module performance issues including latency bottlenecks inconsistent outputs across modules cost overruns from inefficient model usage or failures in multi-step reasoning chains
• Conducts integration testing and end-to-end system evaluation using Gen AI-specific metrics including relevance faithfulness coherence task completion rate and tool-call accuracy in agentic flows and frameworks such as RAGAS DeepEval or custom eval harnesses
• Translates architectural decisions from the AI Architect into implementable engineering tasks and ensures fidelity of implementation to design intent
• Serves as the primary technical escalation point for AI Engineers on implementation blockers

Required Skills:

Artificial Intelligence