Sr. Software Engineer, GenAI

Instrumentl is a mission-driven startup helping the nonprofit sector to drive impact through their SaaS platform. As a Sr. Software Engineer, GenAI, you will own the full lifecycle of AI features, from rapid prototyping to production deployment, while collaborating with cross-functional teams to build and improve AI systems.

Responsibilities:

• 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
• 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)

Requirements:

• 7+ years of professional software engineering experience
• 1+ years working with modern LLMs (as an IC)
• Experience using Python (FastAPI or equivalent)
• Experience with PostgreSQL or any relational language
• Experience with Redis
• Comfortable with SQL, schema design, and building/maintaining data pipelines
• Proficiency in Python (FastAPI, Celery)
• Proficiency in TypeScript/Node
• Familiarity with Ruby on Rails or willingness to learn
• Experience with AWS/GCP
• Experience with Docker
• Experience with CI/CD
• Experience with observability (logs/metrics/traces)
• Experience building tool/function-calling workflows
• Experience with planning/execution loops
• Experience with safe tool integrations
• Ability to thrive in a cross-functional environment
• Ability to translate research ideas into shippable, user-friendly features
• Bias for action and ownership with an eye for speed, quality, and simplicity
• Strong grasp of document ingestion, chunking/windowing, embeddings, hybrid search (keyword + vector), re-ranking, and grounded citations
• Experience with re-rankers/cross-encoders
• Experience with hybrid retrieval tuning
• Experience with search/recommendation systems
• Comfort designing eval suites (RAG/QA, extraction, summarization)
• Familiarity with frameworks like Ragas/DeepEval/OpenAI Evals or equivalent