• Embed pre-trained foundational models (OpenAI, Anthropic, open-source models) into web and enterprise applications using APIs and microservices. • Design and maintain Retrieval-Augmented Generation (RAG) systems, semantic search layers, and vector data workflows. • Construct multi-step AI orchestration chains, agentic workflows, and automated self-repairing coding harnesses. • Build automated evaluation frameworks to quantify AI accuracy, minimize model hallucination, and run error metrics. • Write production-ready backend code, design robust RESTful APIs, and manage data layers. • Implement system safety rules, data privacy guardrails, and prompt tracking to protect user data and shield against vulnerabilities.

Role Description This role designs, builds, and operates agentic AI and retrieval-augmented generation (RAG) services that automate multi-step business workflows safely and reliably. The position partners with engineering and business stakeholders to deliver deployable, observable AI systems with measurable quality, strong guardrails, and ongoing iteration as tools and best practices evolve. Qualifications - Bachelor’s degree in computer science, Engineering, Information Systems, or related field; equivalent practical experience considered. - 5+ years of core software engineering excellence in Python and cloud environments, including at least 1–2 years of specialized, hands-on delivery of production-grade Generative AI and agentic solutions. - Demonstrated experience designing or implementing agentic or tool-orchestrated AI workflows (multi-step execution, tool calling/function calling, reliability patterns). - Practical experience building RAG systems end-to-end (ingestion → chunking → embeddings → retrieval → generation), including vector search/semantic retrieval concepts and tuning for relevance/latency. - Strong hands-on delivery experience building and operating production Python services (APIs, testing, packaging, performance, reliability). - Experience deploying and operating services on AWS, making sound choices for availability, latency, and cost. - Experience with CI/CD and operational best practices for service delivery (build/release automation, environments, monitoring/alerting). Requirements - Working expertise with agent frameworks/orchestration patterns (e.g., LangChain, CrewAI, AutoGen) and safe tool-calling designs (clear tool boundaries, permissions, validation). - Strong understanding of RAG architecture and retrieval optimization (chunking strategies, embedding selection, reranking, evaluation-driven tuning). - Experience with vector stores / semantic search technologies (e.g., OpenSearch, Pinecone, Weaviate, pgvector) and retrieval performance tuning. - Advanced proficiency in Python for backend/service development, including test practices and production troubleshooting. - Skilled in observability for AI systems (structured logging, tracing, metrics) and retrieval quality regressions. - Familiarity with responsible/secure AI patterns in enterprise contexts (least privilege, data access controls, guardrails, and risk-aware design). - Proficiency with AWS deployment patterns (serverless and/or containerized services) and operational readiness (monitoring, alerting, failure modes). - Strong experience with Git-based source control and CI/CD pipelines, plus reliable release and rollback practices. - Clear communication skills and a collaborative, delivery-oriented mindset. Responsibility - Design and build agentic AI workflows that can plan and execute complex, multi-step tasks using approved agent frameworks; ensure predictable behavior through explicit tool boundaries, permissions, and safety controls. - Build and maintain RAG solutions end-to-end, including ingestion pipelines, chunking/embedding approaches, retrieval strategies, and generation prompts—optimized for relevance, latency, and reliability. - Implement retrieval evaluation and continuous improvement loops by defining measurable quality signals (e.g., retrieval relevance/coverage) and iterating based on observed results and regressions. - Integrate tools and data sources using MCP (Model Context Protocol) or equivalent standard interfaces to provide consistent, secure tool access and reduce one-off integrations. - Deploy and operate AI services on AWS (e.g., Lambda, SageMaker, ECS/EKS) with strong operational practices: logging, monitoring, alerting, and well-understood failure modes. - Engineer robust runtime behavior including error handling, retries, fallbacks, circuit breakers, and guardrails to maintain safe, reliable workflows. - Enable workflow automation and integration by identifying high-value repetitive processes and delivering AI-driven automation layers that integrate into enterprise systems and platforms. - Create and maintain technical documentation for architectures, interfaces, evaluation approaches, and operational runbooks to support maintainability and auditability. - Collaborate cross-functionally with product/business stakeholders to translate workflows into well-scoped deliverables and to validate outcomes against measurable success criteria. - Other duties as assigned. Other Duties as Assigned - Provide advisory support to stakeholders on opportunities to improve operational efficiency using agentic workflows and RAG-enabled automation. - Research and recommend emerging AI tooling, evaluation methods, and responsible AI practices that reduce technical debt and improve system quality over time. Benefits - Remote Work/Flexible Scheduling - 401(k) option with employer match of up to 4% - Medical, dental, and vision insurance options and an outpatient mental health benefit - Paid personal/vacation time plus 12 paid holidays - Family/Medical Leave - Tuition assistance - Employee Assistance Program (EAP) - Short- and long-term disability insurance - And more Application Instructions Qualified candidates must apply online through APA’s applicant system and attach a resume and cover letter specifying your salary expectations. Applications that are submitted without both documents are considered incomplete and will not be reviewed for consideration. Once your application is submitted, you will receive a confirmation email. Please make sure to check your Spam folder if you do not receive an email from us. The American Psychological Association is an Equal Employment Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, age, religion, sex, national origin, disability, protected Veteran status, sexual orientation, gender identity, or any other protected categories covered under local law.

• Help define the technical direction for applied ML and AI systems that transform complex data into customer value. • Work across product, engineering, data, and ML teams to take ambiguous 0-to-1 opportunities through model development, evaluation, productionization, experimentation, and measurable customer or business impact.

• Building high-performance API services and implementing complex RAG and Agentic AI architectures. • Designing and implementing end-to-end RAG pipelines, including retrievers, vector stores (e.g., Pinecone, Weaviate, or pgvector), and generators. • Managing orchestration, tool integration, and robust error handling for non-deterministic AI outputs. • Familiarity with evaluation frameworks (e.g., RAGAS, TruLens) to assess performance, grounding accuracy, and hallucination detection. • Iterating systems based on performance metrics and continuous improvement practices.