Sigma360 is looking for a Solutions Data Scientist to be the analytical backbone of our client engagement and system quality work. You'll run rigorous data exercises on real client data, tune Sigma's screening stack for each client's jurisdiction and risk profile, and turn the analytical playbook you pioneer into a self-service product.

We're hiring exceptional data scientists across the junior-to-mid-level spectrum; final compensation reflects experience and level.

About Sigma360

Sigma360 is an MIT-incubated, venture-backed, Series B data and analytics company helping financial institutions, fintechs, and governments manage entity risk. We turn the world's messy, fragmented data into clear answers — powering name screening, sanctions compliance, adverse media monitoring, KYC investigations, and risk research for some of the world's most demanding compliance teams.

Engineers own architecture, AI & data science own model quality, and everyone owns impact.

Why This Role Matters

When a bank evaluates Sigma, the first question is: how well does your system actually work on our data? Everything downstream — whether the deal closes, whether the client trusts us, whether our product gets better — runs through your answer.

• Your analysis decides whether prospects become clients — banks buy Sigma because rigorous data exercises prove the system works on their data; yours is the work that makes the case.
• What you pioneer scales to every client after — the self-service tuning product turns your analytical playbook into leverage, so every client who comes next benefits from the work you do today.
• You find the gaps before clients do — your adversarial testing shapes what R&D builds next, and the failures you catch today become tomorrow's roadmap.

If you're energized by precision — the satisfaction of getting something exactly right when it actually matters — you'll thrive here.

What You'll Do

Own the data exercise function end-to-end. Receive entity lists from prospects and clients, preprocess and load data, run it through Sigma's systems at scale, and deliver clear, reproducible analysis of catch rate and false positive rate. This is the primary function of the role.

Run systematic filter and threshold tuning. Test configurations iteratively to find the optimal tradeoff between catch rate and false positives for each client's data and risk profile. Document what you tested, what changed, and why the result is better. Build scripts that make this process repeatable.

Deliver findings that land. Most of your time is in Databricks and Python — this isn't a writing-heavy role. But when results need to be shared, they go out as short narratives, clean spreadsheets, or well-scoped charts that a compliance executive can act on.

Contribute to the tuning analytics product. Work with product and engineering to help design and build a self-service tuning and analytics feature so clients can run this analysis themselves. Your expertise from manual exercises is the specification.

Stress-test the system. Run the tests a bank validation team would run — adversarial names, transliterations, jurisdictional edge cases, alias patterns — and bring back findings that change what R&D builds next.

What We're Looking For

Required

Statistical and analytical rigor. You design comparisons correctly. You know why naive A/B tests fail. You understand what makes a result meaningful versus coincidental. You catch your own methodological errors.

Expert Python data skills. Pandas, PySpark, scripting — you work with DataFrames all day and you're fast and efficient. You can load millions of rows, join datasets, compute distributions, and build analysis pipelines from scratch.

Meticulous attention to detail. You notice the outlier in row 47,000, investigate why, and document what you find. You check your own work before delivering it. Your analysis can be re-run and audited six months later.

Tolerance for systematic, iterative work. Some of this work involves running the same test with small variations many times. You find that satisfying rather than tedious because you care about finding the right answer, not just an answer.

Explain your methodology. You can defend the choices you made — why this threshold, this sample size, this control — in plain language when a stakeholder asks.

Quantitative foundation. Bachelor's degree in Statistics, Data Science, Mathematics, Computer Science, or a related field — or equivalent practical experience.

Nice to Have

• Databricks experience (notebooks, PySpark, scheduled workflows)
• AML, KYC, sanctions, or financial crime domain knowledge
• Experience with entity matching, fuzzy matching, or record linkage problems
• Comfortable presenting analytical findings directly to clients and fielding their questions live
• Familiarity with model risk management concepts or model documentation standards
• Experience building internal analytics tooling or contributing to product specifications
• SQL proficiency for data exploration and validation

What We Offer

• Remote-first team with high autonomy and ownership
• Competitive compensation and meaningful equity
• Health, dental, vision, and other benefits (or local equivalent)
• Generous time off and a culture that supports learning and growth
• A role where your analytical work has direct, visible impact on revenue and client trust
• Small team environment: you'll have real ownership and real influence from day one

How to Apply

Apply with your résumé and a short note on the most rigorous data exercise you've run — what made it hard, and how did you know your conclusions were trustworthy?

Sigma360 is an equal opportunity employer. We are committed to fair hiring practices and to creating a welcoming environment for all team members. All qualified applicants will receive consideration without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, disability, age, familial status, or veteran status.