MenuData.ai is an AI startup disrupting the food and beverage industry by leveraging large language models to deliver cutting-edge analytics, insights to the largest brands in Food & Beverage. We’re building advanced tools that integrate specialized retrieval over domain-specific data—empowering our clients to make smart, data-driven decisions at scale.

We believe the biggest bottleneck in deploying AI is the accuracy and reliability of retrieval. By combining state-of-the-art LLMs with a robust retrieval-augmented generation (RAG) pipeline, we’re raising the bar for how AI can transform decision-making in the food and beverage space.

We’re looking for a hands-on AI Engineer with end-to-end ownership for designing, building, deploying, and testing large language models—especially those powered by Retrieval-Augmented Generation. You’ll be part of our early technical team, writing reusable and scalable code in an environment that blends engineering rigor with rapid experimentation. If you’re driven by solving real-world problems, comfortable with a wide range of technologies, and passionate about the next generation of applied AI, we’d love to talk.

• Design & Lead RAG Pipelines: Collaborate closely with the CEO (an ex-researcher) and other stakeholders to conceptualize, develop, and benchmark retrieval systems (vector databases, document stores, indexing strategies).
• Architect & Integrate Multi-Agent LLMs: Productionize multi-agent systems with Python backends, orchestrating advanced features like memory, retrieval, and fault recovery with robust, lightweight frameworks.
• Systematize Prompt Engineering: Develop frameworks for prompt optimization, dynamic output structuring, concurrency orchestration, and automated prompt experiments.
• Experiment & Prototype: Rapidly test new LLM features (e.g., fine-tuning, tabular RAG, semantic caching, advanced LLMOps, “prompt-as-program” techniques) while maintaining rigorous production standards for what works.
• Own Evals & Observability: Build evaluation frameworks (deterministic & LLM-based) to measure reliability, performance, and drift. Implement CI/CD pipelines to ensure continuous improvement and fast iteration.
• Collaborate Across the Stack: Integrate with backends in Rust (for representational computing), Go (for application APIs), and Cython (for algorithmic computing), as well as a TypeScript/React frontend for real-time data analytics.
• Champion Quality & Scalability: Write clean, modular, maintainable code; enforce best practices in version control, testing, and deployment.
• Drive Research & Production: Co-lead an internal AI research initiative to monitor and adopt the latest LLM/agent trends. Productionize successful experiments in collaboration with domain experts and product teams.
• Mentor & Grow the Team: Help us attract, interview, and nurture top-tier engineering talent as we build out our founding team.

• Hands-On LLM Experience: Demonstrable expertise in building, tuning, and deploying LLM-based systems, especially with RAG pipelines.
• Strong Engineering Foundation: Proficiency in Python & at least one compiled/concurrent language (e.g. Rust, Go). Comfortable with Docker, Terraform, AWS, and modern CI/CD (GitHub Actions).
• Data & Retrieval Mastery: Familiarity with GraphQL, Postgres, DuckDB, and vector DBs (e.g., Qdrant, Chroma, Pinecone). Skilled in structuring specialized knowledge bases for LLM retrieval.
• Experimental Mindset: Capable of rapid prototyping, robust testing, and continuous improvement. Experience with advanced LLMOps, from fine-tuning to cost/performance optimization.
• Mathematical Aptitude: Familiarity with relevant mathematical disciplines (e.g. linear algebra, optimization, simulation, or operations research).
• Full-Stack Interest: Comfortable working with TypeScript/React or at least open to collaborating with front-end teams building modern web applications (Sass, WebSockets, etc.).
• Excellent Communication: Strong written and verbal communication skills. Ability to distill complex AI topics into actionable insights for teammates and stakeholders.
• Startup Mindset: Prior startup experience (or a strong desire to work in a fast-paced environment) is a plus. Ability to travel to SF Bay Area every other month if not local.

• Passion Projects: Contributions to open-source LLM/agent frameworks (e.g., DSPy, LangChain, Autogen, or others).
• Agentic Systems Experience: Familiarity with multi-agent orchestration, concurrency patterns, and reflective programming.
• Reading & Research: Engaged with technical writing from thought leaders like Lilian Weng, Eugene Yan, Chip Huyen, Karpathy, or swyx.
• Distributed Systems: Expertise or interest in building reactive, distributed platforms at scale.
• Food & Beverage Domain: Any prior experience or curiosity about applying AI to the F&B or hospitality industries.

• High Impact & Ownership: As an early team member, you’ll shape our core AI platform and see your work directly affect the evolution of the food and beverage industry.
• Cutting-Edge AI: Work on state-of-the-art LLM techniques, multi-agent architectures, and retrieval pipelines—driving real value for customers.
• Collaborative Culture: Join a small, tight-knit team of engineers, scientists, and entrepreneurs who value innovation and continuous learning.
• Competitive Compensation & Benefits: We offer a compelling package (equity, healthcare, etc.) and the chance to be part of a fast-growing startup.
• Professional Growth: Expand your skill set and career potential by tackling hard technical challenges and scaling solutions to enterprise-level clients.

If you’re ready to build, deploy, and test advanced LLMs with RAG pipelines—and want to play a pivotal role in an AI startup reshaping the food and beverage industry—send your resume, GitHub/portfolio links, and a brief note on why you’re interested to sunny@menudata.ai.

We can’t wait to see what you will bring to MenuData.ai!