Join a forward-thinking engineering team focused on advancing agentic AI across enterprise platforms. As a Senior AI Software Engineer, you'll lead the design and implementation of intelligent systems capable of planning, executing, and completing multi-step business tasks through secure tool integration and workflow automation.
What You’ll Do
- Architect and deploy AI Agent frameworks using planner/executor patterns, enabling autonomous task completion with controlled, auditable decision-making.
- Develop secure tool integrations with APIs, internal services, and workflow engines, ensuring safe execution, access controls, and compliance safeguards.
- Engineer resilient agent behaviors with deterministic fallbacks, idempotent operations, retry logic, and safe partial-completion strategies.
- Build reusable components including shared tool registries, prompt contracts, memory management systems, and policy enforcement layers.
- Enable product teams through SDKs, reference implementations, and standardized APIs to consistently embed agents across channels.
- Design evaluation systems to measure task success, tool accuracy, response groundedness, latency, cost, and regression across agent versions.
- Implement retrieval-augmented generation (RAG) pipelines that ground agent outputs in authoritative enterprise data with full traceability.
- Develop memory architectures—session, long-term, and semantic caching—with strict privacy and data retention policies.
- Orchestrate prompts using system-level policies, role definitions, and tool-specific guidance to maintain reliable agent behavior.
- Optimize inference services for performance, resilience, and cost-efficiency using batching, caching, async processing, and circuit breakers.
- Establish CI/CD pipelines for agent services, including automated testing, canary deployments, and rollback protocols.
- Implement comprehensive observability with distributed tracing, model telemetry, failure analytics, and incident response runbooks.
- Embed security from the start: manage secrets, enforce least-privilege access, encrypt sensitive data, and maintain tamper-resistant action logs.
- Enforce governance policies such as approval workflows, restricted actions, PII redaction, and defenses against prompt injection.
- Collaborate with Risk and Compliance to ensure alignment with regulatory and enterprise standards.
- Lead technical reviews and mentor engineers on agentic design, production readiness, and engineering excellence.
- Work closely with Product, Architecture, Security, and Data teams to translate business needs into scalable agent-driven solutions.
What We’re Looking For
Candidates should have a Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field—or equivalent hands-on experience. Seven or more years of software development experience is required, with at least three years focused on delivering AI/ML or generative AI systems to production.
Proficiency in Python and at least one backend language (Java, Go, or Node.js) is essential. You should have a strong background in distributed systems, microservices, APIs, and event-driven architectures in cloud environments. Direct experience with LLM applications—including tool calling, function calling, and orchestration frameworks—is critical.
We value rigorous engineering practices: thorough testing, performance optimization, CI/CD implementation, system reliability, and incident response.
Preferred Background
- Proven track record building AI Agents or agentic workflows involving multi-step reasoning, planning, and tool integration.
- Experience implementing RAG systems for enterprise knowledge grounding.
- Familiarity with containerization (Docker) and orchestration (Kubernetes), along with enterprise observability tools.
- Background in regulated industries such as financial services, with understanding of SDLC controls, privacy requirements, and audit readiness.
Technology Environment
Our stack includes Python, Java, Go, Node.js, RESTful APIs, microservices, event-driven architectures, cloud platforms, LLM application frameworks, tool/function calling, orchestration libraries, RAG systems, Docker, Kubernetes, CI/CD pipelines, and enterprise observability solutions.
Compensation and Benefits
This role offers a salary range of $107,360 to $161,000 per year, with eligibility for an annual discretionary bonus. Benefits include comprehensive medical, dental, and vision coverage; retirement planning support; generous paid time off that exceeds statutory requirements; parental leave; flexible work options; education reimbursement; and wellness initiatives.
Work Model
This is a hybrid position requiring presence in the office four days per week. Eligible locations include Johnston, RI; Iselin, NJ; Westwood, MA; Medford, MA; and Phoenix, AZ. Flexible work arrangements are supported within this framework.
Our Culture
We foster an inclusive environment where all individuals are empowered to contribute authentically. Our values center on respect, professionalism, and equitable opportunities for growth. We are deeply committed to diversity and inclusion across all levels of the organization.
Equal Employment Opportunity
We provide fair and equal employment opportunities for all applicants and employees, regardless of age, ancestry, color, citizenship, disability (actual or perceived), ethnicity, gender, gender identity or expression, genetic information, marital or domestic partner status, family status, medical condition, military or veteran status, national origin, pregnancy or related conditions, reproductive health decisions, race, religion, sex, sexual orientation, or any other category protected by applicable federal, state, or local laws.
