Senior LLM Cost Optimizer & Performance Engineer

Data Capital Incorporation; McLean (VA); In loco; USD 160.000 - 230.000; Tempo pieno

Descrizione del lavoro

Data Capital Inc. is seeking a Senior LLM Cost Optimization Engineer to drive enterprise cost reductions for GenAI infrastructure and inference, without compromising quality.

You will lead hands-on optimization across token usage, model selection, and caching, with strong emphasis on observable metrics and cost controls. Ideal candidates demonstrate 7+ years in software/cloud/FinOps, 2+ years with LLMs, and hands-on AWS Bedrock experience.

Competenze

• 7+ years in software, cloud/platform engineering, or FinOps, including 2+ years with LLM platforms.
• Strong Python, SQL, cloud cost analytics, and automation skills.
• Hands-on experience optimizing LLM token usage, model selection, caching, and inference costs.
• Experience with observability/gateway tools (Langfuse, LangSmith, Helicone or similar).
• Strong AWS experience, including Bedrock, Cost Explorer, and cloud cost management.
• Experience building cost dashboards with Grafana/Power BI/QuickSight.
• Must demonstrate measurable production LLM cost savings without compromising quality or performance.

Mansioni

• Analyze and optimize enterprise LLM API usage, token consumption, and inference costs.
• Implement intelligent model routing, prompt caching, and semantic caching.
• Develop AI cost monitoring dashboards, usage analytics, budget controls, and chargeback/showback.
• Optimize AWS Bedrock and other enterprise LLM platforms for cost efficiency.
• Evaluate API-based vs. self-hosted LLM deployment costs and infrastructure utilization.
• Evaluate and optimize AI licensing to eliminate unnecessary platform spending.

Conoscenze

Python

SQL

Automation

Cloud cost analytics

LLM cost optimization

Production cost savings

Strumenti

Langfuse

LangSmith

Helicone

AWS Bedrock

Grafana

Power BI

QuickSight

Descrizione del lavoro

Data Capital Inc. is seeking a Senior LLM Cost Optimization Engineer to drive enterprise cost reductions for GenAI infrastructure and inference, without compromising quality.

You will lead hands-on optimization across token usage, model selection, and caching, with strong emphasis on observable metrics and cost controls. Ideal candidates demonstrate 7+ years in software/cloud/FinOps, 2+ years with LLMs, and hands-on AWS Bedrock experience.