Software Engineer

NewGen Technologies

Herndon, VA, United States

11 days ago

Apply on www.clearancejobs.com

Prepare application

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Expert

Experience required

2 years minimum

Working hours

Regular working hours

Job source

www.clearancejobs.com

Tech stack

Amazon Web Services Cloud Engineering Computer Programming Amazon DynamoDB Systems Analysis Python (Programming Language) Performance Tuning Scrum Methodology Search Technologies Software Engineering Management of Software Versions Enterprise Software Applications

+7 more

Large Language Models Model Validation Generative AI AI Platforms Infrastructure Automation Frameworks Cloudwatch Security Orchestration, Automation & Response

Job description

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 delivery standards
Engage directly with customer stakeholders and technical counterparts to gather requirements and validate solutions

Requirements

TS/SCI CI Poly Clearance
Generative AI (expert level)
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
Prove track record of enterprise-scale architecture design and implementation
Experience with Partner’s 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
Able to travel onsite periodically for meetings and ceremonies