Senior Generative AI Engineer - AWS Bedrock & Orchestration

Quevera LLC; Herndon (VA); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Medical coverage

Dental & Vision

Disability coverage

Life insurance

Education budget

iQTouch Program

401(k) match

Profit-sharing

Job summary

Quevera LLC is seeking a senior GenAI/Cloud Architect to join an onsite engagement in Herndon and Springfield, VA. You will design intelligent model-routing logic, build multi-model orchestration layers with AWS Bedrock and LangChain, and advance production-grade GenAI capabilities within customer Scrum teams.

Your work includes developing conversation-context strategies, prompt standards, and scalable architectures with a focus on availability, performance, and cost control.

Qualifications

• Active TS/SCI clearance with Polygraph required.
• 5+ years of software development and cloud architecture experience.
• 2+ years hands-on AWS experience with production workloads.
• 2+ years experience with Generative AI technologies and LLM deployment.
• Strong programming skills in Python and infrastructure-as-code tools.

Responsibilities

• Design intelligent model-routing logic using ML-based classification to route requests to appropriate LLMs based on context and task complexity.
• Build orchestration layers using AWS Bedrock, LangChain, or custom frameworks to support multi-model workflows.
• Train, evaluate, and iterate on classification models using evaluation frameworks and feedback loops.
• Architect conversation-context analysis, retrieval, and embedding strategies for multi-turn interactions.
• Develop prompt-engineering standards and context-window management to support routing and deployment.

Skills

Python

AWS

GenAI

LLM deployment

Cloud architecture

Security/compliance

Agile/Scrum

Vector databases

Semantic search

Tools

Amazon Bedrock

LangChain

OpenSearch

CloudWatch

ECS

EKS

RDS

DynamoDB

Job description

Quevera LLC is seeking a senior GenAI/Cloud Architect to join an onsite engagement in Herndon and Springfield, VA. You will design intelligent model-routing logic, build multi-model orchestration layers with AWS Bedrock and LangChain, and advance production-grade GenAI capabilities within customer Scrum teams.

Your work includes developing conversation-context strategies, prompt standards, and scalable architectures with a focus on availability, performance, and cost control.