What the role involves
As a Founding Engineer at Convexia, you will build the core agentic frameworks and evaluation systems that power our Source → Diligence → Decide product.
Your Role
Build and iterate on agentic orchestration frameworks: Develop robust systems for tool calling, routing, memory management, guardrails, provenance tracking, and failure recovery to ensure seamless agent performance.
Design evaluation and backtesting harnesses: Create comprehensive tools for our agents and PoS model, including offline replay, regression testing, and confidence calibration to validate and refine system accuracy.
Own end-to-end product delivery: Manage the full lifecycle from data ingestion and processing to user experience and system reliability, incorporating tight feedback loops from customers to drive rapid improvements.
Enhance system performance and correctness: Tackle challenges with messy, real-world inputs like PDFs, tables, slides, non-English sources, and conflicting evidence to deliver reliable results.
Partner with founders on strategy: Collaborate on the product roadmap, customer integrations, and technical direction as we transition from a platform to owning and advancing key assets.
We’re hiring for people that are high-agency and a bit delusional. Specifically, you:
You've built and shipped complex backend or ML systems in production, with a bias toward reliability
You obsess over evaluation, observability, and failure modes
You thrive in ambiguity and move fast without waiting for permission
You communicate clearly and take ownership in low-process environments
Other things we like
- You've been underestimated before
- You've been told you're "too intense"
- You get bored in the absence hard problems
- Hacker house vibes appeal to you
About Convexia
An AI-maximalist pharma platform. We use agents to buy drugs, run clinical trials, and sell for a profit. 10x faster and 20x leaner than incumbents. Sourcing Agent: Mines public/private databases and unstructured global data to surface overlooked preclinical candidates. Scientific Agent: Runs comp bio models (ESM-3, RFdiffusion, Boltz-2, AlphaFold) to assess safety and efficacy in silico. Commercial Agent: Analyzes FDA incentives, pricing dynamics, TAM, competitive landscape, and payer alignment. Clinical Agent: Runs digital twin simulations, evaluates CRO/CMC risk, and builds trial plans to Phase 1. PoS Agent: Evaluates the most critical factors that impact the likelihood of clinical trial success. Built by 2 Stanford CS students who have built 3 startups together before.
Full Convexia profile