AI Engineer

Abacum is the leading Business Planning solution for finance teams to drive performance. By automating reporting, enabling collaboration, and simplifying planning and forecasting, we help finance teams shift from number crunching to driving strategic decisions.

Founded in 2020 by two former CFOs, we've grown into a global team of 100+ people across 30+ nationalities. Headquartered in New York, we have offices in Toronto and Barcelona. We're trusted by industry leaders such as Dish Networks, Strava, BetterUp, Kajabi, JG Wentworth, Abridge, Cortex, and hundreds more.

We have raised over $100m, closing in June 2025 our $60M Series B, led by Scale Venture Partners, with the strong participation of Cathay Innovation, Y Combinator, Atomico, Creandum, and angel operators from Adyen, Zapier, and Twitch.

Our mission is ambitious and we can't do it alone - join Abacum as we build the future of Business Planning!

• Drive continuous innovation within AI Labs by researching cutting-edge technologies and experimenting with new PoCs.

• Design and build sophisticated, multi-provider LLM workflows and autonomous agents capable of advanced reasoning and independent decision-making.

• Building MCP (Model Context Protocol) agents to bridge the gap between LLMs and our proprietary data ecosystems.

• Integrate AI capabilities into existing product workflows to automate and enhance core functionality.

• Optimize AI agent performance through fine-tuning, evaluations, prompt optimization, and system design through RAG pipelines.

• Strong experience with AI agent orchestration frameworks and architectures.

• Background in machine learning or predictive modeling to derive insights from large datasets.

• Knowledge of AI safety, alignment, and responsible AI development practices.

• Practical experience working with Vector Databases (e.g., pgvector, Pinecone, Qdrant, etc) for RAG implementations.

• Bachelor's degree in Computer Science or a related field.
• Deep understanding of Large Language Models (LLMs) and their practical applications.
• Proficiency in prompt engineering, chain-of-thought reasoning, context engineering, and token optimization techniques.
• 5+ years of Software engineering background with expertise in Python and cloud platforms.
• Hands-on experience with AI frameworks such as LangChain and LangGraph.
• Self-motivated with the ability to work independently in a fast-paced, remote-first environment.
• Experience with AI evaluation frameworks, benchmarking, and performance optimization.