Full Stack AI Engineer

Surge IT; Alexandria (VA); On-site; USD 120,000 - 160,000; Full time

Job summary

Surge IT is seeking an experienced Software Engineer to design, develop, and deploy AI-enabled full stack applications for document processing and intelligent search in a federal-friendly environment.

You will collaborate with data scientists, implement accelerators like RAG pipelines, and build secure cloud-native APIs on AWS, while adhering to responsible AI practices and security standards.

Qualifications

• Experience building full stack apps with React, Angular, or Vue and Node.js, Python FastAPI, or Java Spring.
• Hands-on ML/LLM capabilities in production or near‑production environments.
• Strong Python skills for AI workflows and API development.
• Experience with AWS services (Lambda, S3, ECS/EKS, API Gateway, CloudFormation/Terraform).
• Familiarity with vector search, embeddings, RAG architectures, or NLP/LLM systems.
• Experience with DevOps tooling (GitLab/GitHub CI/CD, Docker, Kubernetes).
• Ability to work directly with clients, refine requirements, and deliver iterative prototypes quickly.
• Ability to successfully complete a Public Trust investigation

Responsibilities

• Design, develop, and deploy AI-enabled full stack applications for document processing, intelligent search, and generative AI use cases.
• Implement and integrate AI accelerators such as RAG pipelines, model orchestration, hybrid search, and structured data generation.
• Develop secure, cloud-native backend APIs and microservices (AWS preferred), data ingestion, and workflow automation.
• Collaborate with data scientists to train, finetune, or evaluate ML/LLM models in client systems.
• Apply MLOps best practices for model lifecycle, experimentation, telemetry, CI/CD, testing, and monitoring.
• Ensure compliance with client security requirements, accessibility standards, and responsible AI principles.
• Support rapid prototyping and production hardening aligned to modernization initiatives (e.g., intelligent document management).
• Participate in sprint ceremonies, backlog refinement, and joint design sessions with product owners and leads.
• Produce documentation, architecture diagrams, and deployment artifacts.

Skills

Frontend frameworks

ML/LLM in production

Python programming

AWS cloud

Vector search / embeddings

CI/CD / DevOps

Tools

Docker

Kubernetes

GitHub Actions

Terraform

Job description

This role blends hands‑on software engineering, applied AI, cloud-native development, and integration of generative AI accelerators into mission systems.

Job Description

• Design, develop, and deploy AIenabled full stack applications that support document processing, intelligent search, generative AI use cases, and agentic workflows.
• Implement and integrate reusable AI accelerators such as RAG pipelines, model orchestration layers, hybrid search components, and structured data generation capabilities.
• Develop secure, cloudnative backend APIs and microservices (preferably AWSbased), data ingestion, and workflow automation.
• Collaborate with data scientists to train, finetune, or evaluate machine learning and LLM models implemented within client systems.
• Apply LLMOps best practices for model lifecycle, experimentation, telemetry, CI/CD, testing, and monitoring.
• Ensure solutions comply with client security requirements, federal accessibility standards, and responsible AI principles.
• Support rapid prototyping as well as hardening prototypes to productiongrade systems aligned to client modernization initiatives (e.g., intelligent document management, NLPdriven search, cloud migration).
• Participate in sprint ceremonies, backlog refinement, and joint design sessions with product owners and technical leads.
• Produce documentation, architecture diagrams, and deployment artifacts.

Required Qualifications

• Experience building full stack applications using frameworks such as React, Angular, or Vue; and backend frameworks such as Node.js, Python FastAPI, or Java Spring.
• Handson experience applying machine learning or LLM capabilities in production or nearproduction environments.
• Strong Python skills for AI workflows and API development.
• Experience with AWS services (e.g., Lambda, S3, ECS/EKS, API Gateway, CloudFormation/Terraform).
• Familiarity with vector search, embeddings, RAG architectures, or NLP/LLMdriven systems.
• Experience with DevOps tooling (GitLab/GitHub CI/CD, Docker, Kubernetes).
• Ability to work directly with clients, refine requirements, and deliver iterative prototypes quickly.
• Ability to successfully complete a Public Trust investigation