About the position
As an ML Product Engineer at Tanagram, you'll leverage the latest ML tools and techniques to enable product functionality, including analyzing enterprise-scale codebases for implicit dependencies, implementing recommendation systems for finding code that's similar to a given pattern, and extracting patterns from code reviews and documentation. You should have a good intuition for the right tools to use and how to configure, combine, and tweak them to deliver the best results for our users. We’re a small team of generalists and work across multiple domains. We're looking for meticulous, high-agency people who have good judgment around what problems to solve, the skills (or learning ability) to solve it expediently, and an understanding of the appropriate quality bar given the surrounding business context. We will generally work in-person in San Francisco (our office is in Mission Bay), but are open to remote for the right candidate.
Responsibilities
- Evaluate and build with the best tools in an AI stack: LLM-Evals, Guardrails for AI, CodeAct (agents writing code to fulfill goals), memory for agents (like Mem0).
- Research & apply ML algorithms: clustering techniques, similarity search, entity recognition, etc.
- Build knowledge graphs from multiple data sources.
- Use reasoning models like Qwen2.5-7B-Instruct to refine queries based on existing knowledge.
- Ensure that systems are efficient, maintainable and well-monitored.
- Shape our product roadmap by influencing the sequencing of what we want to build, and/or by talking to potential users and proposing new projects.
Requirements
- Experience working with high-volume data in vector databases.
- Experience with ML/NLP techniques on production projects.
- At least a few years of experience at a fast-growing company or in a user-facing engineering IC role.
- Self-direction and output-oriented: you repeatedly, independently seek out the most valuable thing you could be doing, to achieve scalable results, quickly.
Nice-to-haves
- Experience building knowledge graphs and working with graph databases.
- Experience implementing drift detection between models and the underlying data.
- If you've previously worked at a startup, or founded one yourself.
- Excellent problem-solving and analytical skills.
Benefits
- Challenging work on enterprise-scale codebases and datasets.
- Top-of-market compensation (and a long runway).
- Employee-friendly equity terms (early exercise, extended exercise).
- Your choice of Macbook Pro + computer/office equipment stipend.
- Food stipend/reimbursements on meals.
- Health, dental, and vision insurance.
- Unlimited PTO.
- An opportunity to lead and define our company.
