Position Overview

Orakl Oncology is pioneering a new paradigm in cancer drug development by building the world’s largest cohort of patient-derived organoid (PDO) avatars. Through our unique platform, we generate extensive multi-modal data from these avatars to discover and validate new oncology therapeutics with real-world patient relevance.

We are seeking a Senior AI Engineer to own the technical vision and execution of our AI strategy. This is a uniquely high-impact role at the intersection of AI engineering and the scientific processes developed internally: you will design, build, and operate the production-grade agentic systems that power our predictive oncology platform, and by the same token support the scientists and clinicians working to improve patients’ lives. You will be embedded at the heart of a fast-paced, multidisciplinary team of experimental biologists, data scientists, and engineers.

What You’ll Do

Lead Agentic Strategy & Architecture

• Own the technical vision and architecture for agentic systems at Orakl: multi-step workflows integrating tools, memory and state management, planning, and human-in-the-loop controls.

• Stay at the forefront of the field — continuously monitor state-of-the-art agentic methods, evaluate their applicability to Orakl’s context, and drive adoption of relevant innovations across the team.

• Design, ship, and operate production-grade agentic systems that answer key health challenges for cancer patients, including:

  • Scientist-facing agents that accelerate and improve scientific development workflows (Drug Screen Scoring, Sensitivity-Phenotype Profiling, Protein-Ligand Prediction, and more).

  • Data Quality Agents that continuously monitor and validate the integrity of data generated across our experimental and computational pipelines.

  • Product Agents embedded in our core product to support evidence-based therapeutic decision-making.

Engineering

• Contribute to the development of our flagship predictive oncology platform, by shipping high-quality software features in close collaboration with the engineering team.

• Productionize key models and pipelines (e.g., Sensitivity-Phenotype Profiling) to make them robust, scalable, and ready for use in scientific and commercial contexts.

• Influence ML infrastructure and hardware decisions to ensure training and inference workloads are scalable, reliable, and cost-efficient.

Who You Are

• A builder at heart — you thrive when you’re shipping working systems, not writing perfect specifications.

• Deeply curious about the potential of LLMs and agentic AI, and excited to apply these technologies in a domain where they can genuinely improve health outcomes.

• A collaborative technical leader who enjoys raising the bar across teams through mentorship, clear technical communication, and well-reasoned architectural choices.

• Comfortable navigating ambiguity and operating at the frontier of a fast-evolving field, where the right answers often don’t exist yet.

• Energized by working in a multidisciplinary environment alongside experimental scientists, clinicians, and product engineers.

Minimum Qualifications

• Master’s degree in a quantitative field (Computer Science, Mathematics, Engineering) and 3+ years of experience building production software, including meaningful hands-on experience deploying LLM-powered applications.

• Strong proficiency in Python and modern AI/ML tooling; familiarity with agentic frameworks (e.g., LangChain, LlamaIndex, Strands, or equivalent).

• Proven track record of taking AI systems from prototype to production, including testing, monitoring, and iteration in a real-world environment.

• Solid software engineering fundamentals: API design, data pipelines, version control, cloud infrastructure.

• Ability to influence technical direction through collaboration and constructive challenge, not just authority.

Preferred Qualifications

• Experience designing or operating multi-agent systems (tool use, memory, orchestration, human-in-the-loop).

• Exposure to healthcare, life sciences, or other regulated/high-stakes domains.

• Familiarity with ML infrastructure topics: distributed training, model serving, inference optimization, GPU workload management.

• Prior experience working in early-stage startups or fast-growing deep tech environments.

• Contributions to open-source projects or publications related to LLMs, agentic AI, or applied ML

Recruitment process

1. HR Call — Getting to know each other, aligning on expectations and context.

2. Technical Deep Dive — A deep conversation on your past AI engineering work: architecture decisions, production challenges, and lessons learned.

3. Technical Case — A system design exercise centered on agentic AI, representative of the real problems you’ll face at Orakl.

4. Reference Call — A conversation with one or two people you’ve worked with closely.

5. Founder Interview — A final discussion with our founders on vision, culture fit, and mutual ambitions.