Lab Automation Engineer

Adaptyv Bio

Adaptyv is building an automated lab that lets AI agents run biology experiments. We're entering the era of agentic science where AI models can now design novel proteins, propose hypotheses, and iterate on experimental results. But they can't run the experiments themselves - that's still a manual, months-long process. We're building the infrastructure that gives AI agents access to the physical world. We are one of the fastest growing biotech companies, trusted by leading biopharmas, frontier AI labs, and the techbio companies pushing the field forward. This is a rare chance to help advance some of the most important work happening in biotech today. Our automated lab is powered by a deep software + hardware stack: lab instruments worth millions of USD reverse-engineered into API-controllable hardware, dozens of devices orchestrated through complex workflows, full observability on everything that happens in the lab, processing pipelines for messy physical-world data, and AI systems that troubleshoot production results and accelerate assay development. We’re growing rapidly and are hiring for talented people to scale and support the massive demand for AI-driven wet lab experimentation. ABOUT THE ROLE You'll build work-cell orchestration, instrument drivers, protocol scheduling, error-recovery logic, and monitoring. Physical systems fail in ways pure software doesn't — a plate gets stuck, a liquid handler skips a well, a temperature controller drifts. Your job is to make the system handle all of it gracefully. This is a broad, hands-on role for a strong engineer who wants their code to drive real machines and see it run the same day. WHAT YOU'LL DO * Build orchestration software that coordinates liquid handlers, plate readers, incubators, and robot arms — handling timing dependencies, state, and error recovery. * Reverse-engineer and develop instrument drivers and APIs. Each instrument speaks a different protocol (serial, USB, TCP/IP); you work out how it talks and build a clean abstraction over it. * Model and execute complex multi-step protocols reliably — a single run can span dozens of steps across multiple instruments. * Build error-recovery logic so that when something fails mid-run, the system retries, skips, alerts, or pauses depending on the failure mode. * Create monitoring and observability for work-cell health: instrument status, run progress, error rates. * Debug across the software–hardware boundary — figuring out whether bad data is a comms, firmware, calibration, or code problem. * Work closely with lab automation engineers, the rest of the software team, and the scientists running production. STACK TypeScript and Python, Postgres (Supabase), Modal for compute. We control instruments with open-source Python tooling like PyLabRobot and PyHamilton wherever we can, rather than proprietary vendor GUIs. WHAT WE'RE LOOKING FOR * Strong software engineering skills. You write production code in Python and/or TypeScript — well-structured and maintainable, not just prototypes. * Comfortable at the hardware-software boundary. You've built software that drives physical devices, or you're excited to. You can read a protocol spec, debug a flaky connection, and reason about timing. * Lab automation experience is a strong plus. Familiarity with PyHamilton, PyLabRobot, Opentrons, or similar tooling helps — as does a background in robotics, industrial automation, IoT, or embedded systems. * Maker and hacker attitude. You like figuring out how closed systems work and building the thing that makes them work better. Bonus if you're comfortable with electronics, microcontrollers, or a 3D printer when an integration needs a physical fix. * AI-native builder. It's 2026 — you build with coding agents like Claude Code as a default, and you have sharp judgment about what they produce. * Self-starter and independent. You define what needs building from how the lab actually works, not just what's in the ticket. * Reliability-minded. The lab runs 24/7; you design systems where one instrument failing doesn't cascade through the whole work cell. Biology background not required — but you should be excited that the code runs real experiments. DETAILS * Location: Lausanne, Switzerland (on-site — you need hands-on access to physical instruments). * Type: Full time * Start date: ASAP Application deadline We are reviewing applicants on a rolling basis.

Adaptyv Bio

Adaptyv is building an automated lab that lets AI agents run biology experiments. We're entering the era of agentic science where AI models can now design novel proteins, propose hypotheses, and iterate on experimental results. But they can't run the experiments themselves - that's still a manual, months-long process. We're building the infrastructure that gives AI agents access to the physical world. We are one of the fastest growing biotech companies, trusted by leading biopharmas, frontier AI labs, and the techbio companies pushing the field forward. This is a rare chance to help advance some of the most important work happening in biotech today. Our automated lab is powered by a deep software + hardware stack: lab instruments worth millions of USD reverse-engineered into API-controllable hardware, dozens of devices orchestrated through complex workflows, full observability on everything that happens in the lab, processing pipelines for messy physical-world data, and AI systems that troubleshoot production results and accelerate assay development. We’re growing rapidly and are hiring for talented people to scale and support the massive demand for AI-driven wet lab experimentation. ABOUT THE ROLE You'll build out antibody developability at Adaptyv — the panel of assays that separates a nice binder from a manufacturable, stable, well-behaved therapeutic. Aggregation, thermostability, self-association, polyreactivity, solubility, viscosity, and chemical liabilities: you'll build the experimental stack that flags these early, and make it something customers can order as a product. These assays exist today as a scattered, bespoke collection. Your job is to turn them into one coherent, automated, high-throughput developability assessment — and to connect the experimental data to in-silico prediction so the lab and the models reinforce each other. You'll develop the assays hands-on, work with lab automation to scale them, and work with the software and ML teams to model the data and make it useful for protein designers. You'll lead the science and stay at the bench. WHAT YOU'LL DO * Build and validate a developability assessment panel hands-on: thermostability (DSF/nanoDSF), aggregation and self-association (SEC, HIC, AC-SINS, DLS), polyreactivity/nonspecificity, solubility, and chemical-liability assessment. * Turn that panel into a productized, high-throughput service customers can order against their antibody campaigns. * Partner with lab automation to scale and automate the assays for reproducible, fast turnaround. * Work with the software and ML teams to structure developability data and connect it to computational developability prediction. * Interpret results and advise customers on liabilities, risk, and what to engineer next. * Set the scientific standard for what developability data we trust and report. WHAT WE'RE LOOKING FOR * Deep, hands-on experience assessing antibody developability — you know the assay panel cold and have used it to triage real antibody campaigns. * Applied industry experience. You've done this in an antibody discovery, engineering, or development setting where decisions and timelines were on the line — not primarily in an academic research project. This is the core requirement. * Strong grasp of what makes a biologic developable — the link between early biophysical signals and downstream manufacturability and stability. * Builder who moves fast. You want to stand up new capabilities and productize them, not run a fixed service. * Interdisciplinary. You collaborate naturally with automation engineers and with software/ML people, and you're excited about closing the loop between wet-lab data and predictive models. * Data fluency (scripting, working with structured datasets) is a strong plus. DETAILS * Location: Lausanne, Switzerland (on-site) * Type: Full time * Start date: ASAP Application deadline We are reviewing applicants on a rolling basis.

Adaptyv Bio

Adaptyv is building an automated lab that lets AI agents run biology experiments. We're entering the era of agentic science where AI models can now design novel proteins, propose hypotheses, and iterate on experimental results. But they can't run the experiments themselves - that's still a manual, months-long process. We're building the infrastructure that gives AI agents access to the physical world. We are one of the fastest growing biotech companies, trusted by leading biopharmas, frontier AI labs, and the techbio companies pushing the field forward. This is a rare chance to help advance some of the most important work happening in biotech today. Our automated lab is powered by a deep software + hardware stack: lab instruments worth millions of USD reverse-engineered into API-controllable hardware, dozens of devices orchestrated through complex workflows, full observability on everything that happens in the lab, processing pipelines for messy physical-world data, and AI systems that troubleshoot production results and accelerate assay development. We’re growing rapidly and are hiring for talented people to scale and support the massive demand for AI-driven wet lab experimentation. ABOUT THE ROLE We are going from roughly 25 people to roughly 50 in the next twelve months. We have close to 30 roles open right now, across protein scientists, lab automation engineers, backend and product engineers, ML people, and commercial. Hiring is currently run by the founders, on top of everything else the founders do. That is the single biggest thing standing between us and the company we're trying to build. This is the hire that fixes it, and we want to aim high with it. Not a recruiter who works a req list. Someone who owns talent as a function: what we hire for, how we assess it, how we pitch it, who does the recruiting, and what the org actually looks like on the other side of doubling. The hard part of this job is that our roles don't sit in one talent pool. In the same week you might be trying to find a protein biochemist who can read a sensorgram, an engineer who can make a liquid handler behave, and a backend engineer who has never touched biology. Those people read different signals, hang out in different places, and are sold with different pitches. You have to be able to hold all of that at once, and know which one you're talking to. We would love someone who can speak both languages well enough to spot exceptional people themselves. You don't need a PhD and you don't need to ship code. You do need enough real understanding of what our scientists and engineers actually do that you can tell the difference between someone who sounds impressive and someone who is. This is a Lausanne role. Most of the company is here, most of the people you'll hire will be here, and the job is much easier when you can walk over to a hiring manager and argue about a candidate in person. WHAT YOU'LL DO * Own hiring end to end. Define what we're hiring for with the team, write and post the roles, build the pipeline, run the process, and close people. * Build the recruiting team. As we scale, you'll hire and manage specialist recruiters, most likely a technical recruiter first. You'll be a player-coach for a long time before you're purely a manager. * Own the inbound pipeline. We get a lot of applicants and a real share of them are strong. Right now good people can get lost in the pile. Making that never happen is one of the most valuable things you can do here. * Run our work trials. A lot of our best hires come through paid work trials rather than interview loops. Scheduling them, matching them to the right people internally, and making them a great experience for the candidate is core to the job. * Make the pitch. You'll often be the first human a candidate talks to. You're selling the mission, and you should genuinely believe it. * Own Ashby and push it further. Our ATS is already wired into AI tooling: automated candidate scoring, assisted review, templated and scheduled candidate comms. You'll inherit that and be expected to make it better, not merely operate it. * Work with hiring managers across biology, software, automation, and commercial. Different teams, different bars, different definitions of good. You'll help each of them get sharper about what they actually need. * Build the parts of the org that hiring touches: leveling, compensation bands, interview structure, onboarding, and how we make offers. Fast and light, not corporate. WHAT WE'RE LOOKING FOR * You've hired technical people at real depth, for several years, in a high-growth environment. You've owned searches that mattered and closed people who had other options. * You can talk to scientists and to engineers. You understand enough biology and enough software or lab automation to run a credible conversation, ask a sharp follow-up, and form your own view of someone's quality. This is the thing we care most about and the thing most recruiters cannot do. * You are not a mercenary. We are not looking for someone optimizing for placements or fee cycles. We want someone who cares about what we're building, who wants the company to be excellent in ten years, and who treats every hire as a long-term bet rather than a filled seat. * You use AI tools seriously. We run on Claude Code and similar tooling across the company, including in hiring. The best version of this person is automating their own pipeline, writing their own scripts against Ashby, and finding leverage the rest of us haven't thought of. If your instinct is that recruiting is purely a human craft that shouldn't be automated, we'll frustrate each other. * Self-starter, high autonomy. Nobody will hand you a prioritized req list. You'll figure out what's most broken, fix it, and tell us what you did. * Fast learner. You'll be dropped into unfamiliar technical domains constantly and expected to get to a useful level of understanding quickly. * Startup speed, not corporate process. Good candidates disappear in days. We'd rather move fast and occasionally be wrong than run a beautiful process that loses people. * Good taste in people, and the confidence to hold a bar. Part of this job is telling a founder that the person they liked isn't good enough. * Bonus: experience with the Swiss labor market, hiring in European biotech or deep tech, or building a talent function from nothing. WHAT THIS ROLE IS NOT * Not a coordinator role. You'll do scheduling when it needs doing, but if that's what you want to do all day, this will bore you. * Not a pure people or HR generalist role. Payroll, benefits, and Swiss employment admin exist and are mostly handled. Talent is the job. * Not an agency-style seat. You're not filling reqs handed down to you. You're deciding, with the founders, what we should be hiring for at all. WHY THIS ROLE IS INTERESTING Most talent leaders inherit a hiring machine and tune it. You'd be building one, at a company that is unusual enough to be genuinely fun to pitch: an automated lab that AI agents can run experiments in, used by the best pharma companies and the best AI labs in the world. The people you hire over the next two years will decide whether that works. There are not many jobs where the leverage is that direct. Application deadline We are reviewing applicants on a rolling basis.