AI Engineer

Embedded Alliance, Inc.; Herndon (VA); On-site; USD 120,000 - 210,000; Full time

Benefits offered by this job

401(k)

401(k) matching

Dental insurance

Employee assistance program

Employee discount

Flexible schedule

Flexible spending account

Health insurance

Health savings account

Life insurance

Paid time off

Parental leave

Professional development assistance

Referral program

Tuition reimbursement

Vision insurance

Job summary

Embedded Alliance, Inc. is seeking an AI Engineer to implement LLM models inside an analytic environment for a classified enterprise setting.

The role focuses on agent-based components, retrieval pipelines, and production-ready integrations that enable end-to-end orchestration on the platform. Responsibilities include building REST APIs in Python, enabling data retrieval and system integration, and handling memory, prompts, and embedding generation.

Qualifications

• Active TS Clearance (Top Secret required).
• Solid Python with production-level code experience.
• Experience building or consuming REST APIs.
• Comfort with databases and SQL.
• Exposure to LLMs or a RAG prototype including agent work.
• Bachelor’s in computer science or related field; further experience considered.
• Hands-on experience building LLM-integrated applications, RAG workflows, or retrieval-based systems.
• Knowledge of transformer behavior, context windows, and retrieval pitfalls.
• 8+ years of software engineering, with recent AI/ML application development.

Responsibilities

• Implement orchestration logic, tool integrations, and memory handling within agent-based apps.
• Support document processing, including embedding generation and prompt assembly.
• Build Python REST APIs to enable data retrieval and agent workflows.
• Process/transforms data for AI workflows with Postgres schemas and query performance.
• Handle testing, deployment, and classified enterprise constraints.
• Design and lead the team to deliver end-to-end orchestration within the platform.

Skills

Python

REST APIs

LLMs

RAG workflows

agent-based programming

SQL

production-grade code

Cloud/ AWS

Testing and deployment

Education

Bachelor’s in computer science or related field

Tools

FastAPI

Flask

Postgres

Vector databases

Embedding models

Job description

The AI Engineer role at Embedded Alliance focuses on implementing LLM models inside an analytic environment for a classified enterprise setting. The position involves building agent-based components, retrieval pipelines, and production-ready integrations that support end-to-end orchestration on the platform.

Location and Compensation

• Location: Herndon, VA (onsite)
• Salary: USD 120,000 - 210,000 per year
• Minimum experience: 8 years
• Education: Bachelor’s in computer science or a related field

Core Responsibilities

• Implement orchestration logic, tool integrations, and memory handling within agent-based applications
• Support document processing, including embedding generation, retrieval configuration, and prompt assembly
• Build Python REST APIs to enable data retrieval, system integration, and agent workflow support
• Process and transform structured and unstructured data for AI workflows, including working with Postgres schemas and addressing query performance
• Handle testing, deployment, and the constraints of a classified enterprise environment
• Design and lead the team to deliver end-to-end orchestration within the platform

Required Qualifications

• Active TS Clearance (Top Secret required)
• Solid Python with production-level code experience
• Experience building or consuming REST APIs
• Comfort with databases and SQL
• Some hands‑on exposure to LLMs or a RAG prototype, including work such as an agent you built or a course/side project
• Curiosity demonstrated through practical learning and experimentation
• Bachelor’s in computer science or a related field, with additional experience considered in lieu
• Hands‑on experience building LLM-integrated applications, RAG workflows, or retrieval-based systems
• Working familiarity with agent concepts for at least one AI framework
• Understanding of transformer behavior, why context windows matter, and where retrieval can fail
• Enough production experience to make informed opinions about reliability and maintainability
• 8+ years of software engineering experience overall, including recent hands‑on work in AI/ML application development
• Strong Python and fluency with common data and AI libraries
• Demonstrated experience with LLM-integrated applications, RAG workflows, or similar retrieval-based systems
• Working knowledge of agent-based programming
• Solid grounding in fundamentals such as transformers, LLM behavior, data processing, and model integration patterns
• Experience designing or integrating REST APIs
• Production engineering habits including testing, reliability, and deployment

Technologies

• Python
• REST APIs
• Postgres
• SQL
• LLMs
• RAG
• FastAPI
• Flask
• Vector databases
• Embedding models
• Semantic search
• Docker
• AWS
• MCP

Clearance Requirements

• Top Secret (Required)

Benefits

• 401(k)
• 401(k) matching
• Dental insurance
• Employee assistance program
• Employee discount
• Flexible schedule
• Flexible spending account
• Health insurance
• Health savings account
• Life insurance
• Paid time off
• Parental leave
• Professional development assistance
• Referral program
• Tuition reimbursement
• Vision insurance

Level Indicators

• Junior-level: Working software engineer seeking to move into AI
• Mid-level: Shipped AI-enabled work in addition to an established foundation
• Senior-level: Design and lead the team to provide end to end orchestration within the platform

Nice to Have

• FastAPI or Flask
• Vector databases, embedding models, semantic search
• Docker and containerized development
• AWS or comparable cloud environments
• MCP or similar agent-to-tool protocols
• Anything built independently that can be discussed