Software Engineer, AI/ML GenAI

• Design and Deploy AI Systems: Build resilient, observable agentic LLM systems (including tool planning, function calling, and multi-step workflows) for grant discovery, application drafting, and document parsing.
• Own RAG Pipelines: Manage end-to-end Retrieval-Augmented Generation, including content ingestion, chunking strategies, hybrid retrieval, re-ranking, and grounded citations.
• Manage Embeddings: Select, evaluate, and migrate embedding models; maintain vector stores (e.g., pgvector, Qdrant, Pinecone); monitor drift.
• Collaboration: Work cross-functionally with Product and Design teams; run experiments (A/B testing); contribute to reliability practices like alerts and incident response.
• Code Quality: Write maintainable code, add tests and documentation, and ensure cost/latency optimization., Note: This role supports Instrumentl's mission to drive impact in the nonprofit sector. The company uses AI tools to assist in the hiring process, but final decisions are made by humans.

• Experience: 5+ years in professional software engineering, with at least 2 years focused on modern LLMs.
• LLM Agentic Systems: Proven experience building tool/function-calling workflows, planning loops, and safe integrations (e.g., LangChain, LangGraph, LlamaIndex).
• RAG Expertise: Strong understanding of document ingestion, embeddings, hybrid search, re-ranking, and grounding.
• Vector Stores: Hands-on experience with embedding model selection/versioning and vector databases (pgvector, Qdrant, Pinecone, Weaviate, Milvus).
• Evaluation: Experience designing eval suites (RAG/QA, extraction, summarization) using frameworks like Ragas, DeepEval, or OpenAI Evals.
• Infrastructure: Proficiency in Python (FastAPI, Celery), GCP/AWS, Docker, CI/CD, and observability tools.
• Data Skills: Comfortable with SQL, schema design, and data pipeline development.

Nice to Have

• Startup experience in fast-paced environments.
• Familiarity with responsible AI, red-teaming, and domain-specific safety policies.
• Practical experience with fine-tuning (SFT/LoRA/instruction-tuning).

• Salary Range: $175,000 - $220,000 per year (US-based).
• Equity: Included in compensation package.
• Health Insurance: 100% covered for employees (50% for dependents).
• Time Off: Generous PTO policy including parental leave.
• Retirement: 401(k).
• Equipment: Company laptop + home workstation stipend.
• Perks: Company retreats and opportunity to work with nonprofit partners.