Software Development Engineer II
Advanced
Washington, DC, United States
3 months ago
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Experienced
Experience required
3 years minimum
Working hours
Regular working hours
Job source
Tech stack
Adobe InDesign
Application Programming Interfaces (APIs)
Artificial Intelligence
Amazon Web Services
Microsoft Azure
Cloud Engineering
Continuous Integration
Software Design Patterns
Distributed Systems
Fault Tolerance
Monitoring of Systems
Python (Programming Language)
+25 more
Key Management
Scrum Methodology
Regression Testing
Microsoft SharePoint
Software Engineering
Systems Integration
Data Logging
Google Search
Large Language Models
Multi-Agent Systems
Prompt Engineering
Backend
Containerization
Kubernetes
Infrastructure Automation Frameworks
Information Technology
Slack
Deployment Automation
Production Code
Virtual Agents
Dynatrace
Api Management
Serverless Computing
Docker
Web Api
Job description
The Software Development Engineer II role would be supporting the GRACE Development Team within ARPA-H. This role focuses on building production-scale agentic AI systems, LLM-powered applications, backend services, and cloud-based AI infrastructure supporting GRACE, ARPA-H’s production AI assistant.
- mplement and enhance GRACE’s agentic workflows including tool-calling, multi-step reasoning, memory, and A2A communication patterns
- Build and maintain MCP client-side integrations enabling agents to discover and invoke tools
- Develop tool definitions, schemas, retry logic, error handling, and formatting for GRACE’s tool ecosystem
- Contribute to multi-agent orchestration patterns that are reliable and production-ready
- Implement LLM orchestration logic including prompt construction, context management, model selection, and response parsing
- Build and maintain RAG pipeline capabilities including query formulation, citation grounding, ranking, and hallucination mitigation
- Develop prompt engineering patterns and system prompts supporting multiple LLM providers
- Contribute to context window budget management including truncation, summarization, and pagination logic
- Build LLM evaluation components including grounding assessments, regression tests, safety checks, and quality metrics
- Develop secure backend application features and API integrations end-to-end
- Integrate with internal and external APIs including Dimensions, Google Search, Slack, SharePoint, and LLM provider APIs
- Contribute to monitoring, logging, distributed tracing, and system observability
- Implement fallback, retry, and graceful degradation patterns for AI service dependencies
- Work within Microsoft Azure infrastructure including Azure Functions, API Management, Container Apps, and Azure OpenAI Service
- Contribute to CI/CD pipelines, deployment automation, and infrastructure-as-code practices
- Participate in design reviews, sprint planning, and retrospectives
- Collaborate closely with product managers, researchers, designers, and senior engineers to implement technical solutions
- Ensure strong privacy, security, and compliance across all systems and integrations
- Write production-quality code that is readable, tested, documented, and maintainable
Requirements
Do you have experience in Python?, Do you have a Master’s degree?, * Bachelor’s or Master’s degree in Computer Science, Software Engineering, or related field, or equivalent practical experience
- 3+ years of professional software engineering experience building and operating production systems
- Proven experience contributing to the delivery of real products in fast-paced environments
- Strong proficiency in Python and at least one additional backend programming language
- Experience with algorithms, distributed systems, APIs, and software design patterns
- Experience with AWS, GCP, or Microsoft Azure cloud platforms
- Experience with Docker, containerization, and CI/CD pipelines
- Experience building features on top of LLMs including tool-calling, RAG, multi-step reasoning, and context management preferred
- Familiarity with A2A communication patterns and multi-agent orchestration frameworks preferred
- Familiarity with MCP integrations and prompt engineering concepts preferred
- Experience with LLM evaluation, grounding assessment, and AI system testing preferred
- Familiarity with token economics, context budget management, and prompt efficiency preferred
- Experience with Azure Functions, API Management, Container Apps, or Azure OpenAI Service preferred
- Knowledge of secrets management, least-privilege access, and security-conscious engineering preferred
- Strong communication, collaboration, and problem-solving skills
- Ability to work collaboratively in cross-functional environments
- Experience in startup, early-stage, or regulated environments preferred
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Apply on indeed.comGood distractions
Talks and stories from around this role — technically off-topic, practically not.
Moments
Explore playlistsVideos
See allRelated articles
See all
CH
Chris Heilmann
about 2 years ago
LM
Luis Minvielle
What Are Large Language Models?
almost 3 years ago
EM
Eli McGarvie
Highest Paying Tech Companies for Developers
over 3 years ago
LM
Luis Minvielle
Why Upskilling And Reskilling is Important For Developers
over 2 years ago
LM
Luis Minvielle
How to Become an AI Engineer
over 2 years ago
CH
Chris Heilmann
Dev Digest 120 - Apple and peers
about 2 years ago