• Design, implement, and optimize automated workflow protocols using FAST platforms and other advanced liquid handling systems. • Develop software tools for instrument control, workflow automation, and integration with data pipelines. • Define integration schemas for module-to-module system-level integration. • Break down systems into submodules for testing, troubleshooting, and staged integration. • Drive system-level validation and performance benchmarking in collaboration with CDMO partners. • Build versatile tools for workflow scheduling, data acquisition, and pipeline integration. • Support system data analysis and instrument performance monitoring. • Partner with assay development scientists to translate proteomics and molecular biology protocols into robust automated workflows. • Work with hardware and software engineers to align mechatronic subsystems and automation platforms with assay requirements.

• Own major features end-to-end. From design discussions to production deployment. • Build across the stack. Frontend, backend, and everything in between. • Instrument and learn. Use metrics and user feedback to refine what we build. • Shape the foundation. Influence architecture, tools, and engineering practices. • Keep security and ethics front and center. We’re handling sensitive healthcare data — trust is everything. • We’re tackling complex engineering problems — building intelligent systems that can understand messy, real-world healthcare data, automate workflows, and communicate with empathy and reliability.

• Own major features end-to-end. From design discussions to production deployment. • Build across the stack. Frontend, backend, and everything in between. • Instrument and learn. Use metrics and user feedback to refine what we build. • Shape the foundation. Influence architecture, tools, and engineering practices. • Keep security and ethics front and center. We’re handling sensitive healthcare data — trust is everything. • Tackle complex engineering problems — building intelligent systems that can understand messy, real-world healthcare data, automate workflows, and communicate with empathy and reliability.

• Own Autocomplete end-to-end: product feel, model behavior, latency, reliability, quality, and iteration velocity. • Build the benchmark that matters: not a vanity leaderboard — a real eval harness that tracks what users actually experience (acceptance rate, edit distance, time-to-accept, latency, regressions by language/project type). • Run tight experiment loops: tweak prompts, decoding, routing, caching, context packing, and ranking — then measure, learn, repeat. • Form strong opinions: FIM vs next-edit, speculative decoding, reranking, context window strategy, model routing, and how to trade off quality vs speed without lying to yourself. • Work directly with model creators: test new models early, give actionable feedback, and ship upgrades fast when something is truly better. • Ship constantly: small improvements weekly, bigger improvements monthly, and a compounding moat over time.