Sr. Software Engineer, GenAI

Remote (United States)

About the Role

This opportunity is for a Sr. Software Engineer, GenAI to join an AI engineering team and own AI-powered product features from concept through production. The role focuses on grant discovery, data ingestion, RAG systems, ranking, agentic workflows, and production evaluation for AI-driven search and matching experiences.

You will work in a product pod, reporting to an AI engineering lead, with direct access to founders and high ownership over undefined technical problems. This role is hands-on and production-focused, requiring strong Python engineering, relational database design, modern LLM experience, and the ability to build reliable AI systems that operate at scale.

Status: Full-Time

Pay: $175,000 – $220,000 per year

What You’ll Do

Build Agentic AI Systems and Ship Them to Production

• Build tool-using LLM systems that can plan, call tools, and execute multi-step workflows for grant discovery, data ingestion, and research assistance
• Build agentic data-processing pipelines that crawl the web, extract messy source data, deduplicate records at scale, and structure data into clean, queryable databases
• Create data foundations that other teams can build on
• Turn prototypes into resilient production services with clear fallback strategies, cost controls, and latency budgets

Own RAG and Ranking End to End

• Own the full RAG lifecycle, including ingestion, chunking, embedding strategy, hybrid retrieval, re-ranking, citations, and grounding
• Build ranking and scoring systems that match grants to nonprofits, universities, and foundations using advanced relevance techniques
• Continuously improve recall and precision as datasets grow
• Keep retrieval indices healthy, reliable, and production-ready

Ship Safely and Raise the Engineering Bar

• Build evaluation and observability systems so AI outputs remain grounded, safe, and cost-effective
• Treat LLM behavior as non-deterministic by design and build systems accordingly
• Partner directly with founders and product pod teammates on complex, undefined problems
• Write clear, maintainable, well-tested code
• Build reusable systems that can expand across teams

Qualifications

• 7+ years of professional software engineering experience
• Deep, recent, multi-year experience with Python
• Strong relational database and schema design skills
• Solid computer science fundamentals
• Demonstrated track record of owning complex systems end to end, from design through production reliability
• At least 1 year of hands-on individual-contributor experience building with modern LLMs

Nice to Have

• Deep production experience with RAG, including hybrid search, re-ranking or fusion methods, and grounded citations
• Hands-on experience with LangChain, LangGraph, or LlamaIndex
• Experience with vector databases beyond pgvector, such as Pinecone, Qdrant, or Milvus
• Experience building end-to-end agentic data-processing systems, including crawling, deduplication, and data structuring
• Experience with AI evaluation and observability, including golden datasets, precision versus recall, LLM-as-judge, and drift monitoring
• Ruby on Rails experience
• Deep SQL experience
• Experience with AWS or GCP
• Experience with Docker and CI/CD
• Startup experience and comfort working in fast, scrappy, low-process environments

Benefits

• 100% covered health, dental, and vision insurance for employees
• 50% dependent coverage
• Generous paid time off, including parental leave
• 401(k)
• Company laptop
• Home-office stipend
• Bi-annual company retreats
• Equity participation