Descripción del empleo
About The Role
Sapphire Labs is looking for a Senior GenAI / Bedrock Engineer to join a high-impact client initiative through one of our strategic partners. This is a client-facing role focused on building and scaling production-grade Generative AI capabilities on AWS.
The ideal candidate has real-world experience shipping multi-tenant LLM solutions in production using AWS Bedrock — not just experimentation or research projects. We are looking for an engineer with strong platform and infrastructure instincts who can build reliable, scalable, observable GenAI systems.
What You’ll Do
-Design and implement production-grade GenAI applications using AWS Bedrock
-Build and maintain scalable multi-tenant AI platform architectures with strong tenant isolation and security practices
-Develop and deploy containerized AI workloads on AWS ECS
-Optimize token usage, inference costs, and workload performance across LLM pipelines
-Implement observability, monitoring, and validation frameworks for AI systems
-Develop safeguards for hallucination detection, validation workflows, and responsible AI behaviors
-Collaborate directly with client engineering leadership in a highly technical, client-facing environment
-Support scalable deployment, reliability, and operational excellence practices for GenAI services
Key Experience
-Production experience with AWS Bedrock
-Multi-tenant SaaS architecture
-AI / LLM infrastructure engineering
-MLOps, monitoring, and observability
-AWS ECS, CI/CD, and cloud-native architecture
-Strong client-facing communication skills
Required Skills
-5+ years of software engineering experience with recent hands-on GenAI platform work
-Hands-on AWS Bedrock experience including:
-Model invocation
-Bedrock Agents
-Guardrails
-AWS ECS architecture for containerized workloads and multi-region deployments
-Strong experience building and scaling multi-tenant SaaS platforms
-Strong understanding of data isolation and tenant configuration patterns
-Token optimization experience including:
-Consumption modeling
-Cost analysis
-Workload profiling
-MLOps practices including:
-Model validation frameworks
-Hallucination detection
-Observability and monitoring
-Strong cloud architecture and backend engineering fundamentals
-Advanced English proficiency for direct client engagement
Desirable Skills
-LangChain, LlamaIndex, or similar AI orchestration frameworks
-Azure AI Services exposure for multi-cloud environments
-Java backend integration experience
-Familiarity with DAMA-DMBOK or DCAM frameworks
-Experience working with cybersecurity or regulated industry platforms
-Experience with CI/CD pipelines and infrastructure automation
What We’re Looking For
We are specifically looking for engineers who have shipped production-grade, multi-tenant LLM solutions on AWS Bedrock. This is not a research, prompt engineering, or experimentation-focused role — strong platform engineering, cloud architecture, operational ownership, and production experience are essential.
Sapphire Labs is a nearshore product development partner founded in Texas in 2022. We embed senior engineers, designers, and product managers directly into your team — same tools, same standups, same time zone — so you can ship faster without the overhead of full-time hiring. With 60+ team members across the US and Latin America, we focus on engineers with 5+ years of experience who tackle complex challenges in fintech, SaaS, and marketplace platforms. Learn more about our nearshore software development services or get in touch to discuss your project.
