Full Stack Engineer (AI Platform)

Bright Metro
Washington, DC, United States
1 day ago
Apply on www.juju.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Job source

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Airflow Amazon Web Services Computing Platforms Computer Engineering Continuous Integration Data Infrastructure Data Visualization Django Web Framework Elasticsearch Python (Programming Language)
+22 more
PostgreSQL Redis TypeScript ReactJS Large Language Models Prompt Engineering Indexer Backend Git SC Clearance Event Driven Architecture AI Platforms Kubernetes Information Technology Apache Kafka Machine Learning Operations Celery Restful APIs Terraform Data Pipelines Api Management Docker

Job description

We are seeking a Senior Full Stack Engineer (AI Platform) to help build and evolve our internal AI-powered platform. This role is designed for an experienced engineer who can own production systems end-to-end-from backend services and data infrastructure to intuitive, analyst-facing applications-and who is excited to apply modern AI capabilities within a robust software platform.

The ideal candidate is a strong full-stack engineer first, with experience building AI- and LLM-powered applications in production. You are comfortable working across the stack, making pragmatic architecture decisions, and taking ownership from technical design through deployment. You thrive in a fast-paced, small-team environment, are comfortable navigating ambiguity and complex technical problems, and bring the judgment and experience to help raise the bar for the engineers around you.

Reporting to the VP of Technology, you will design and build core applications and services that power our platform, partnering directly with technical leadership to shape product and architectural direction. You will also collaborate with our customer-facing team to translate analyst and customer needs into scalable, reliable software., * Own features end-to-end across the platform: Django REST APIs and data models, React/TypeScript UI, workflow pipelines, and LLM agent services, from technical design through coding, testing, and production

  • Partner with technical leadership on architecture and roadmap: turn product vision into system designs, pressure-test ideas, and help drive the technical direction of the platform
  • Build LLM-powered systems on AWS Bedrock: tool-using agents, RAG retrieval over OpenSearch, prompt engineering, evaluation, and cost/usage controls
  • Develop data and ML workflows in Metaflow orchestrated on Argo Workflows/Kubernetes: ingestion, enrichment, classification, and document processing at scale
  • Design for the whole system: PostgreSQL schema, OpenSearch indexing and search, event-driven processing (Kafka, Redis/Celery), and clean API contracts between services
  • Collaborate with the customer-facing team to create solutions that support customer needs
  • Work in agile sprints with the engineering team, making informed decisions between competing solutions

Requirements

  • U.S. Citizen eligible to work on government contracts; active or prior SECRET clearance preferred
  • Bachelor’s and 5 years of experience, or master’s degree and 3 years of experience, in Computer Science, Computer Engineering, or a related technical field
  • 5+ years building production software, with demonstrated ownership of full-stack systems
  • Expert-level Python, with deep Django (or equivalent framework) and PostgreSQL experience
  • Strong TypeScript/React skills, comfortable building complex, data-heavy interfaces
  • Experience building LLM applications: agents, tool calling, RAG, prompt engineering, and evaluation against hosted model APIs (e.g., AWS Bedrock)
  • Experience with search infrastructure (OpenSearch/Elasticsearch) and event-driven architectures (Kafka, Celery/Redis, or similar)
  • Hands-on with AWS, Docker, Kubernetes, Git, and CI/CD; comfortable reading and modifying Terraform

Ideal Candidates

  • Experience with ML/data orchestration (Metaflow, Argo, Airflow) or NLP pipelines
  • Experience in compliance-constrained environments
  • Experience with data visualization and analyst-facing tools
  • Startup instincts: bias to ship, comfortable with ambiguity

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.juju.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

1:20 min

Identifying multi-disciplinary talent for developer experience engineering roles

Hazal Mestci +1 · Coffee With Developers

6:21 min

Investigating push inefficiencies with upstream Git experts

Jonathan Creamer · Coffee With Developers

3:55 min

Demonstrating semantic routing thresholds with the Redis vector library

2:07 min

Inspecting default bridge architectures and custom Docker networks

Oliver Seitz Oliver Seitz · World Congress 2025

3:03 min

Career evolution in data engineering and AI platforms

Maria Apazoglou · Coffee With Developers

56 sec

Favorite git commands and the importance of patch commits

Eileen Uchitelle Eileen Uchitelle +1 · Coffee With Developers

Videos

See all

Related articles

See all