Founding Engineer

Our current product is an inference platform built with quantitative trading rigor. It enables AI teams to quickly switch models across inference providers and optimize inference cost.

Our team comes from quantitative trading and high-frequency derivatives backgrounds, with experience building, trading, and risk-managing complex systems at scale.

Role

You will work with the quantitative researchers and own the production systems that serve the platform's routing, pricing, and risk models.

You would be responsible for:

• Routing and optimization engine: productionize constrained optimization models that filter, score, and select providers across requests, subject to user constraints such as latency, cost, and uptime, as well as platform constraints such as capacity and rate limits
• Predictive signal infrastructure: build the serving layer for quantitative performance and risk signals, including latency distributions, provider health forecasts, and pricing changes, that feed real-time routing decisions at the edge
• Data pipeline: build and maintain quant-grade data collection, transformation, and serving infrastructure for platform measurements, including token usage, realized costs, TTFT, success and failure rates, and provider health signals, to specifications defined by the research team
• Backtesting and simulation: build frameworks to evaluate routing strategies under stress scenarios, including provider degradation, price changes, capacity shocks, and partial outages
• Metrics and validation: build aggregation logic for operational metrics such as P50/P95 latency, uptime, and error rates, data integrity validation, and holdout testing to confirm model improvements against defined targets
• Provider integrations: build and maintain adapters across a growing set of LLM providers, each with its own API shape, streaming behavior, and failure modes
• Billing and metering: build accurate usage tracking across providers with fundamentally different pricing models
• SDKs: build Python and TypeScript clients that serve as drop-in replacements for existing provider SDKs

• Production backend systems experience in Python and TypeScript
• Experience productionizing quantitative, optimization, or ML models into low-latency serving systems
• Comfort with numerical computing: you can read an optimization spec, implement it, debug it, and reason about edge cases
• Distributed systems experience: multi-region services, consistency tradeoffs, and debugging under real load

Strong Pluses

• Background in quant finance, trading systems, or fintech infrastructure
• Edge compute, including CDN-layer request handling and globally distributed systems
• Billing or metering systems where precision is a hard requirement
• SDK design and API ergonomics
• Familiarity with LLM provider APIs such as OpenAI, Anthropic, Google, Mistral, etc.

We are building a small, high-agency team. We value ownership, intellectual honesty, independent thinking, and fast execution. We care about substance over appearance.

Pulled from the full job description

• Parental leave
• 401(k)
• Retirement plan
• Paid time off
• Vision insurance
• Health savings account
• Dental insurance, We believe in identifying high-agency, driven talent and incentivizing them to do exceptional work. Our compensation package is market-leading, with meaningful equity upside., * 401(k)
• Dental insurance
• Flexible schedule
• Health savings account
• Paid time off
• Parental leave
• Relocation assistance
• Retirement plan
• Vision insurance