Agentic AI & ML Software Development Engineer
Phase2 Technology, Washington, District of Columbia, United States
Job Number: R0238284
The Opportunity
We are looking for an experienced Agentic AI & ML Software Development Engineer to serve as a strategic technical expert for ARPA-H, helping conceptualize, create, and execute advanced research and development programs to accelerate better health outcomes. You will work with world‑class scientists and engineers to develop high‑impact solutions to society’s most challenging health problems, providing strategic assessments of new technologies and facilitating commercialization of successfully developed technologies.
What You’ll Work On
Design and maintain core agentic systems, including reasoning, planning, memory, tool use, and multi‑agent workflows.
Build and evolve application‑layer infrastructure such as tool‑calling, MCP integration, A2A communication, and context‑window management.
Lead LLM orchestration and RAG capabilities, including prompt design, retrieval quality, grounding, and hallucination mitigation.
Translate product requirements into clear technical designs and ship end‑to‑end features quickly and reliably.
Prototype and experiment with new agentic capabilities, analyze results, and iterate based on user behavior.
Ensure high observability and reliability through instrumentation, SLOs, guardrails, and collaboration with infrastructure engineering.
Uphold engineering excellence by writing high‑quality code, mentoring teammates, and enforcing strong privacy, security, and compliance practices.
You Have
7+ years of experience with software engineering, building and operating production systems.
Experience in high‑velocity environments, owning and shipping complex products end‑to‑end.
Proficiency in Python and at least one other backend language such as Java, Go, or Rust.
Experience in big‑tech environments building customer‑facing AI platforms or developer tools at scale.
Experience building and operating systems on major cloud platforms such as AWS, GCP, or Azure.
Experience with containerization and working within CI/CD pipelines.
Experience in prompt engineering and LLM behavior across model families.
Experience with token economics such as cost‑per‑query awareness, context budget management, and prompt efficiency.
Knowledge of modern backend frameworks, async patterns, algorithms, data structures, APIs, and software design patterns.
Bachelor’s degree in Computer Science or Software Engineering.
Nice If You Have
Experience in healthcare, life sciences, or other regulated domains.
Experience in security‑conscious engineering, including input validation, output sanitization, audit logging, and responsible AI guardrails.
Experience in startup or early‑stage environments, 0‑to‑1 product building.
Experience with MCP at the client or consumer layer, including how agents discover and invoke tools via MCP.
Ability to work comfortably with ambiguity and a high sense of urgency.
Self‑starter who operates within a fast‑paced environment.
Master’s degree in a relevant field.
Compensation
Salary range: $86,800.00 to $198,000.00 (annualized USD). Benefits include health, life, disability, financial, and retirement programs, paid leave, professional development, tuition assistance, work‑life programs, and dependent care. The posting will close within 90 days from the posting date.
Identity Statement
Applicants will complete an identity verification process using biometrics and AI. Photo may be taken during interviews to verify identity and prevent fraud.
Candidate AI Usage Policy
Use of artificial intelligence tools to assist with interview responses is prohibited unless explicit permission is provided.
Work Model
Remote : May require some in‑person work at a Booz Allen or customer facility.
Hybrid : Expected to work from a Booz Allen facility frequently; may also visit a customer facility.
Onsite : Work primarily at a Booz Allen office or customer facility.
Commitment to Non‑Discrimination
All qualified applicants will receive consideration for employment without regard to disability, veteran status, or any other protected status.
#J-18808-Ljbffr
The Opportunity
We are looking for an experienced Agentic AI & ML Software Development Engineer to serve as a strategic technical expert for ARPA-H, helping conceptualize, create, and execute advanced research and development programs to accelerate better health outcomes. You will work with world‑class scientists and engineers to develop high‑impact solutions to society’s most challenging health problems, providing strategic assessments of new technologies and facilitating commercialization of successfully developed technologies.
What You’ll Work On
Design and maintain core agentic systems, including reasoning, planning, memory, tool use, and multi‑agent workflows.
Build and evolve application‑layer infrastructure such as tool‑calling, MCP integration, A2A communication, and context‑window management.
Lead LLM orchestration and RAG capabilities, including prompt design, retrieval quality, grounding, and hallucination mitigation.
Translate product requirements into clear technical designs and ship end‑to‑end features quickly and reliably.
Prototype and experiment with new agentic capabilities, analyze results, and iterate based on user behavior.
Ensure high observability and reliability through instrumentation, SLOs, guardrails, and collaboration with infrastructure engineering.
Uphold engineering excellence by writing high‑quality code, mentoring teammates, and enforcing strong privacy, security, and compliance practices.
You Have
7+ years of experience with software engineering, building and operating production systems.
Experience in high‑velocity environments, owning and shipping complex products end‑to‑end.
Proficiency in Python and at least one other backend language such as Java, Go, or Rust.
Experience in big‑tech environments building customer‑facing AI platforms or developer tools at scale.
Experience building and operating systems on major cloud platforms such as AWS, GCP, or Azure.
Experience with containerization and working within CI/CD pipelines.
Experience in prompt engineering and LLM behavior across model families.
Experience with token economics such as cost‑per‑query awareness, context budget management, and prompt efficiency.
Knowledge of modern backend frameworks, async patterns, algorithms, data structures, APIs, and software design patterns.
Bachelor’s degree in Computer Science or Software Engineering.
Nice If You Have
Experience in healthcare, life sciences, or other regulated domains.
Experience in security‑conscious engineering, including input validation, output sanitization, audit logging, and responsible AI guardrails.
Experience in startup or early‑stage environments, 0‑to‑1 product building.
Experience with MCP at the client or consumer layer, including how agents discover and invoke tools via MCP.
Ability to work comfortably with ambiguity and a high sense of urgency.
Self‑starter who operates within a fast‑paced environment.
Master’s degree in a relevant field.
Compensation
Salary range: $86,800.00 to $198,000.00 (annualized USD). Benefits include health, life, disability, financial, and retirement programs, paid leave, professional development, tuition assistance, work‑life programs, and dependent care. The posting will close within 90 days from the posting date.
Identity Statement
Applicants will complete an identity verification process using biometrics and AI. Photo may be taken during interviews to verify identity and prevent fraud.
Candidate AI Usage Policy
Use of artificial intelligence tools to assist with interview responses is prohibited unless explicit permission is provided.
Work Model
Remote : May require some in‑person work at a Booz Allen or customer facility.
Hybrid : Expected to work from a Booz Allen facility frequently; may also visit a customer facility.
Onsite : Work primarily at a Booz Allen office or customer facility.
Commitment to Non‑Discrimination
All qualified applicants will receive consideration for employment without regard to disability, veteran status, or any other protected status.
#J-18808-Ljbffr