• Design agentic systems & ship AI to production: Turn prototypes into resilient, observable services with clear SLAs, rollback/fallback strategies, and cost/latency budgets. Build tool‑using LLM “agents” (task planning, function/tool calling, multi‑step workflows, guardrails) for tasks like grant discovery, application drafting, and research assistance. • Own RAG end‑to‑end: Ingest and normalize content, choose chunking/embedding strategies, implement hybrid retrieval, re‑ranking, citations, and grounding. Continuously improve recall/precision while managing index health. • Manage embeddings at scale: Select, evaluate, and migrate embedding models; maintain vector stores (e.g., pgvector/FAISS/Pinecone/Weaviate/Milvus/Qdrant); monitor drift and rebuild strategies. • Fine‑tune & build evaluation: Run SFT/LoRA or instruction‑tuning on curated datasets; evaluate the ROI vs. prompt engineering/model selection; manage data versioning and reproducibility. Create offline and online eval harnesses (helpfulness, groundedness, hallucination, toxicity, latency, cost), synthetic test sets, red‑teaming, and human‑in‑the‑loop review. • Collaborate cross‑functionally while raising engineering standards: Work side by side with Product, Design, and GTM on scoping, UX, and measurement; run experiments (A/B, canaries), interpret results, and iterate. Write clear, maintainable code, add tests and docs, and contribute to reliability practices (alerts, dashboards, incident response).

• The Full-Stack Python Developer will work closely with clients, digital leaders, solutions architects, and technical/ functional leads across Guidehouse digital teams and market segments to support client projects and provide solutions for growth efforts and capabilities build-out. • Serve as a key member of the modernization team to support technical challenges/demos, building innovative solution prototypes using cloud architectures and software technologies. • Solutions architecture and hands-on engineering/full-stack development of scalable and secure distributed systems using modern software technologies and programming, Cloud Native and microservices architecture, containerization, and API-First design patterns. • Work collaboratively with user experience designers, platform engineers, product owners, solution architects, and business analysts, the Cloud Applications Full Stack Developer will design, build, test, and deploy high-value, operationally resilient software products on the AWS cloud platform that satisfy functional and non-functional requirements.

• Build software systems used by millions of low-income Americans, helping to put dollars back in their pockets • Build iOS and Android apps using Vue + TypeScript + Capacitor • Develop significant server-side software using Python and Flask, backed by Postgres and Redis; leverage AWS offerings as well as other open source technologies • Create software that is reliable, scalable, and maintainable • Effectively communicate with team members during projects, code review, etc. • Contribute to building our engineering culture and processes as we continue to scale • Collaborate on deciding on the right projects, building great solutions, and helping your team succeed • Work with our Product and Design team to scope projects and execute on innovative products • Participate in our on-call rotation

• Gain a deep understanding of what Alma members do, how they operate, and where their pain points are. • Work in our backend space (~60% of the role) while tackling work full stack as needed to support projects with frontend-oriented goals (~40% of the role) • Design, develop, and implement maintainable and scalable product features using modern web technologies (Python, Django, MySQL). • Develop both member-facing and internal-facing features around onboarding, scheduling, and client management. • Collaborate with Alma managers, PMs, and designers to conceptualize and build solutions for practical problems facing Alma members. • Ensure applications and services meet Alma's standards for software including performance, scalability, and security.