Job Number: R0248051 Agentic AI and LLM Applications Software Development Engineer, Senior
The Opportunity: The GRACE team at ARPA-H is building the next generation of agentic AI to transform how the agency accelerates research, makes decisions, and ships products at scale. GRACE is ARPA-H's production AI assistant, and we are evolving it into an ecosystem of autonomous, multi-agent systems.
We are a small, startup-minded team that ships fast and owns what we build end-to-end. We are looking for a senior SDE who lives at the application layer: designing and building the agentic workflows, LLM integrations, tool-calling systems, and AI-powered features that GRACE users interact with every day. Your focus is on what runs on top of the platform: the agents, the orchestration, the prompts, the pipelines, and the product.
The best person for this role starts with the user. They ask why before they ask how. They communicate clearly, give and receive feedback well, and make the people around them better. They are a self-starter with a high bar, a high sense of urgency, and genuine empathy for the people whose work they are making better.
What You'll Do:
- Design and build GRACE's core agentic workflows: multi-step reasoning, planning, memory, and tool-use across single and multi-agent systems
- Implement and evolve A2A communication patterns at the application layer, enabling GRACE agents to collaborate and hand off tasks
- Build and maintain the tool-calling layer: tool definitions, input/output schemas, error handling, retry logic, and result formatting
- Own the MCP client-side integration: how GRACE agents discover, invoke, and compose tools exposed via MCP servers
- Design multi-agent workflows that are reliable, observable, and debuggable in production, not just in demos
- Own LLM orchestration at the application layer: prompt construction, context management, model selection logic, and response parsing
- Build and maintain RAG features: query formulation, result ranking, citation grounding, and hallucination mitigation
- Implement and iterate on prompt engineering patterns and system prompts that drive GRACE's quality and consistency across OpenAI GPT, Anthropic Claude, and Google Gemini
- Manage context window budgets: know when to truncate, summarize, or paginate, and build the logic that makes those decisions correctly
- Build evaluation pipelines for LLM quality: grounding assessment, regression testing, safety checks, and A/B experimentation on prompt and model changes
- Stay sharp on token economics: write prompts and pipelines that are cost-efficient without sacrificing output quality
- Translate ambiguous product requirements into clear technical designs and ship them fast
- Build new GRACE capabilities end-to-end: from backend application logic through to the API contract the frontend consumes
- Rapidly prototype new agentic features, run experiments, collect data, and iterate based on real user behavior
- Collaborate closely with product, UX, applied science, and operations; listen well, ask good questions, and build the right thing rather than the obvious thing
- Own the quality of what you ship: write tests, handle edge cases, and make sure your features degrade gracefully when upstream dependencies fail
- Instrument agentic workflows with tracing, logging, and metrics so failures are diagnosable and regressions are caught before users report them
- Define and monitor application-level SLOs: tool call success rates, response quality, and latency from the user's perspective
- Build fallback and guardrail logic for AI services: what happens when a model returns something unsafe, off-topic, or structurally wrong
- Work closely with the infra engineer to understand system-level constraints and design application behavior that respects them
- Write production-quality code: readable, tested, reviewed, and documented
- Communicate technical decisions clearly to both engineers and non-engineers; no one should have to guess what you decided or why
- Participate actively in design reviews; push back when something is over-engineered or under-specified
- Mentor and unblock other engineers; bias toward ownership and fast iteration
- Ensure strong privacy, security, and compliance in all application logic and data handling
Join us. The world can't wait.
You Have:- 7+ years of experience with software engineering, including building and operating production systems
- Experience in high-velocity environments where you owned and shipped complex products end-to-end
- Experience in Python and at least one other backend language
- Experience building and operating systems on major cloud platforms, including AWS, Google Cloud Platform, or Azure
- Experience with containerization and working within CI/CD pipelines
- Knowledge of modern backend frameworks, async patterns, distributed systems, APIs, data pipelines, and software design patterns
- Ability to be a clear, direct communicator who gives and receives feedback well, works with empathy, and makes the people around them better
- Ability to be a self-starter with a high bar and high sense of urgency, including not waiting to be told what to do next
- Bachelor's degree in Computer Science or Software Engineering
Nice If You Have:- Experience building production systems on top of LLMs, including tool-calling, RAG, multi-step reasoning, and context management
- Experience with multi-agent (A2A) architectures and orchestration frameworks in production, not just in prototypes
- Experience building LLM evaluation and regression testing pipelines
- Experience in startup or early-stage environments, including 0-to-1 product building
- Experience in big tech building customer-facing AI platforms or developer tools at scale
- Experience in security-conscious engineering, including input validation, output sanitization, audit logging, and responsible AI guardrails
- Experience in healthcare, life sciences, or other regulated domains
- Knowledge MCP at the client/consumer layer, including how agents discover and invoke tools via MCP
- Knowledge of token economics, including cost-per-query awareness, context budget management, and prompt efficiency
- Ability to demonstrate a strong intuition for prompt engineering and LLM behavior across model families, including why Claude and GPT respond differently to the same prompt and designing for it, and demonstrate comfort with ambiguity
Skills Assessment As part of Booz Allen's skills first hiring process, candidates must complete the required skills assessment to ensure they meet the Basic Qualifications for this role. Candidates must complete the assessment and meet the minimum proficiency threshold to continue in the hiring process.
CompensationAt Booz Allen, we celebrate your contributions, provide you with opportunities and choices, and support your total well-being. Our offerings include health, life, disability, financial, and retirement benefits, as well as paid leave, professional development, tuition assistance, work-life programs, and dependent care. Our recognition awards program acknowledges employees for exceptional performance and superior demonstration of our values. Full-time and part-time employees working at least 20 hours a week on a regular basis are eligible to participate in Booz Allen's benefit programs. Individuals that do not meet the threshold are only eligible for select offerings, not inclusive of health benefits. We encourage you to learn more about our total benefits by visiting the Resource page on our Careers site and reviewing Our Employee Benefits page.
Salary at Booz Allen is determined by various factors, including but not limited to location, the individual's particular combination of education, knowledge, skills, competencies, and experience, as well as contract-specific affordability and organizational requirements. The projected compensation range for this position is $86,800.00 to $198,000.00 (annualized USD). The estimate displayed represents the typical salary range for this position and is just one component of Booz Allen's total compensation package for employees. This posting will close within 90 days from the Posting Date.
Identity StatementAs part of the hiring process, we will ask you to complete an identity verification process that leverages advanced biometrics and artificial intelligence to ensure authenticity and protect against identity fraud. You are expected to be on camera during interviews and assessments. We reserve the right to take your picture to verify your identity and prevent fraud.
Candidate AI Usage PolicyAI is a part of our daily work at Booz Allen, and we are committed to the responsible and ethical use of AI tools. However, we want to ensure a fair candidate process based on
your own skills and knowledge. As part of this commitment, the use of artificial intelligence (AI) or other tools to assist with responses during interviews (whether in-person or virtual) is prohibited
unless permission is explicitly provided.
Work ModelOur people-first culture prioritizes the benefits of collaboration, whether it occurs in person or virtually. To support engagement and effective communication, employees working virtually are generally expected to have their cameras on during meetings.
- Remote: If this position is listed as remote, there may still be occasions when you are required to work in person at a Booz Allen or customer facility.
- Hybrid: If this position is listed as hybrid, you will be expected to work from a Booz Allen facility frequently, in alignment with leadership expectations and the needs of the role. You may also be required to work from or visit a customer facility.
- Onsite: If this position is listed as onsite, work will primarily be performed at a Booz Allen office or customer facility, where employees will collaborate directly with colleagues and customers as required by the role.
Commitment to Non-DiscriminationAll qualified applicants will receive consideration for employment without regard to disability, status as a protected veteran or any other status protected by applicable federal, state, local, or international law.
Never miss an opportunity! Create an alert based on the job you applied for.