Gen AI Software Engineer

Aqua IT; Springfield (VA); On-site; USD 150,000 - 230,000; Full time

Job summary

Aqua IT in the United States seeks a highly experienced engineer to support a critical GenAI optimization engagement for a large enterprise. The role requires deep AWS cloud Architecture expertise and hands-on experience with modern GenAI workflows, model routing, and orchestration.

You will design scalable enterprise platforms, implement cost-aware, secure pipelines, collaborate in Agile teams, and deliver thorough documentation and architecture artifacts to ProServe standards.

Qualifications

• 5+ years of software development and cloud architecture experience.
• 2+ years of hands-on AWS experience with production workloads.
• 2+ years of Generative AI technologies and LLM deployment.
• Strong Python and infrastructure-as-code (IaC) skills.
• Experience with vector databases and semantic search technologies.
• Expert-level knowledge of AWS services including Bedrock, OpenSearch, CloudWatch, ECS/EKS, RDS/DynamoDB.

Responsibilities

• Architect Gen AI solutions that scale to enterprise workloads with high availability and cost management.
• Build and maintain orchestration layers to manage multi-model workflows.
• Develop prompt engineering standards and context management for accurate routing and history analysis.
• Collaborate with stakeholders, participate in Agile ceremonies, and deliver architecture diagrams and handoff artifacts consistent with ProServe standards.

Skills

Python

IaC

GenAI

Architecture design

Problem solving

Communication

Tools

Bedrock (Amazon Bedrock)

OpenSearch

CloudWatch

ECS/EKS

RDS/DynamoDB

LangChain

Vector databases

Job description

Aqua IT is seeking a highly experienced and seasoned expert engineer to support a critical Generative AI optimization engagement for a large-scale enterprise customer. This role requires deep technical expertise in AWS cloud architecture and cutting-edge GenAI technologies, with a focus on enterprise-scale optimization, modernization, and operational excellence.

Required Technical Expertise:

Model Routing & Orchestration

• Design and implement intelligent model routing logic using ML-based classification to direct requests to appropriate LLMs based on conversational context, task complexity, and performance requirements
• Build and maintain orchestration layers (e.g., using AWS Bedrock, LangChain, or custom frameworks) to manage multi-model workflows
• Train, evaluate, and iterate on classification models that drive routing decisions using evaluation frameworks and feedback loops

Conversation Contextualization

• Architect and implement conversation context analysis systems that extract intent signals and contextual features from multi-turn interactions to inform routing decisions
• Design context retrieval and embedding strategies to analyze conversational history and accurately interpret user intent across multi-turn interactions
• Develop prompt engineering standards and context window management techniques to support accurate intent classification and routing across production use cases

Enterprise Platform Engineering

• Architect Gen AI solutions that scale to enterprise workloads — including high-availability design, performance optimization, and cost management
• Apply Gen AI platform best practices: observability, model evaluation, guardrails, responsible AI controls, and versioning
• Design and maintain data extraction and transformation pipelines to support model training, evaluation, and integration with enterprise applications

Delivery & Collaboration

• Participate fully in Agile/Scrum ceremonies: sprint planning, daily standups, retrospectives, and sprint reviews
• Collaborate with the Engagement Manager to track progress, surface risks, and ensure delivery aligns with contractual commitments
• Produce clear technical documentation, architecture diagrams, and handoff artifacts consistent with ProServe delivery standards
• Engage directly with customer stakeholders and technical counterparts to gather requirements and validate solutions

Basic Requirements

• 5+ years of software development and cloud architecture experience
• 2+ years of hands-on AWS experience with production workloads
• 2+ years of experience with Generative AI technologies and LLM deployment
• Proven track record of enterprise-scale architecture design and implementation
• Experience with NatSec customers
• Deep understanding of GenAI foundation models and deployment patterns
• Strong programming skills in Python and infrastructure-as-code tools
• Experience with vector databases and semantic search technologies
• Expert-level knowledge of AWS services including: Amazon Bedrock, OpenSearch Service, CloudWatch, ECS/EKS, RDS/DynamoDB
• Strong understanding of security automation and compliance frameworks
• Ability to work independently and drive initiatives with minimal oversight
• Strong problem-solving and analytical thinking capabilities
• Experience leading technical discussions and influencing architecture decisions
• Comfortable working in ambiguous, fast-paced environments
• Customer-obsessed mindset with focus on delivering measurable outcomes

Preferred Qualifications:

The ideal candidate will be a seasoned expert who can immediately contribute to complex technical challenges, prototype innovative solutions, and transfer knowledge effectively to customer teams. This role requires someone who can balance strategic thinking with hands-on implementation and deliver enterprise-grade solutions under tight timelines.