Agentic AI Engineer, Life Science

Company Description

Algen is an AI-native precision medicine company harnessing the power of CRISPR and functional genomics to transform drug discovery and development. A spin-out from the laboratory of Nobel Laureate Professor Jennifer Doudna, Algen was founded at the forefront of gene-editing innovation. We combine cutting-edge CRISPR technologies with advanced AI approaches to systematically modulate disease biology at scale and accelerate the path to effective treatments. Join us in redefining what's possible in AI-powered drug discovery.

Job Description

As an Agentic AI Engineer (Life Science), you’ll build the software that lets an AI agent plan a scientific analysis, choose tools and recover when a step fails. You’ll work with biologists and chemists to define what a successful analysis looks like, then use those criteria to decide which changes to ship. The work includes bringing the latest advances and original ideas into production. The ideal candidate combines strong engineering execution with a quantitative mindset and an interest in AI agents for scientific discovery.

Responsibilities

• Advance the agent harness by bringing the latest research and open-source developments into production and experimenting with new approaches to multi-agent coordination, model routing, memory, planning, and tool use.
• Work with biologists and chemists to turn real research questions into test cases. Agree on what evidence an answer needs and record the steps a scientist would need to check it.
• Compare changes against a baseline on representative tasks. Measure scientific correctness, completion rate, latency and cost before deciding whether to release a change.
• Make long-running analyses resilient. Run code in a sandbox with scoped tool access, save progress and let interrupted jobs resume without repeating completed work.
• Trace production failures from the agent’s decision through its tool calls and outputs. Reproduce the failure, fix it and add a test that catches it on the next release.

Qualifications

• MUST HAVE: 2+ years of industry experience building production software, with hands-on ownership of a backend service, infrastructure component or full-stack feature.
• MUST HAVE: Familiarity with LLM APIs, tool calling, agent runtimes, or workflow orchestration.
• MUST HAVE: Research or production experience building an LLM-powered agent that calls tools or coordinates a workflow. You can explain a design choice you made and how you tested it.
• MUST HAVE: Experience using data to judge a system change. You can design a repeatable comparison, investigate inconsistent results and explain the tradeoffs to colleagues.
• Ability to take an engineering problem from design through testing, deployment and debugging, and to write code that teammates can maintain.
• Ability to move between research questions, data analysis, system design, and production implementation.
• Experience or strong interest in AI for science, scientific agents, computational research, or automated scientific discovery.
• Experience building modern web applications (e.g. React, TypeScript, FastAPI, or similar frameworks).
• Ability to move fast, own features end-to-end, and operate with high autonomy.
• High standards for code quality, maintainability, and engineering excellence..

Preferred

• Experience designing benchmarks for LLMs, reviewing outputs with domain experts or replaying past runs to test for regressions.
• Experience with durable workflows, task queues, sandboxed code execution or tools for inspecting distributed jobs.
• Experience with LLM post-training, including fine-tuning models for tool use or scientific tasks
• Experience developing agent systems for scientific discovery, particularly self-evolving agents.
• Research or graduate-level experience in machine learning, computational biology or another quantitative field.