🚀 Mission Highlights

As a Scientific Software Developer at Entalpic, you will sit at the intersection of high-performance computing (HPC), quantum chemistry, and machine learning. You will turn raw compute into the large-scale, high-quality computational datasets that power our discovery platform. You will own the data generation engine behind Entalpic's atomistic modelling: operating multiple HPC clusters in parallel, automating computational workflows (e.g., for DFT), and making it dramatically easier to launch, monitor, and interpret calculations at scale.

You will work closely with computational chemists to transform scientific workflows into production-quality software. You will own the codebase and develop the software infrastructure to deploy, orchestrate, and progressively automate large-scale computational chemistry workflows across multiple HPC centres, integrating AI agents to monitor calculations, analyse results, recover from failures, and recommend next steps.

One of the objective being to generate transformative large-scale datasets spanning adsorbates on surfaces, bulk properties, transition states, etc. working closely with ML scientists to turn these datasets into high-performance models. You will be a key contributor to Entalpic’s discovery platform, covering surface chemistry, electronic and functional materials, and atomic-scale manufacturing processes (ALD, ALE, CVD) for semiconductors, batteries, photovoltaics, and beyond. You will also contribute to HPC grant applications, benchmarking, allocation reports, publications, and the continuous improvement of our computational infrastructure.

✨ Role & Responsibilities

This position directly supports the company's mission of discovering materials and processes to optimize carbon-intensive industries. You will be responsible for:

• Multi-cluster HPC operations: Execute large scale workflows on multiple HPC clusters simultaneously (e.g. Jean Zay, LUMI, Leonardo, Adastra, GCP), including GPU-accelerated routines. Help with benchmarking and tune performance across different CPU and GPU architectures, and keep large campaigns running reliably.
• Large-scale computational chemistry dataset generation: help build, execute and curate datasets across a broad chemical space: organometallics, adsorbate on surfaces, bulks, transition states, etc. Own data quality end-to-end.
• Workflow automation & agentification: Advance our DFTBuddy approach to automate the computational chemist's routine: making it easier to launch, babysit, visualise, and interpret DFT calculations. Harden remote workflows against SSH interruptions, SLURM walltime limits, runner restarts, and HPC cluster-specific issues, reducing human-in-the-loop bottlenecks. Develop useful UI tools and agentic recommendations to help monitor and debug large-scale campaigns. Help build out our active learning framework so it can be deployed on HPCs.
• Data management: Help ensure data is parsed and archived correctly using google cloud buckets, PostgreSQL and MongoDB. Partner closely with ML scientists to design datasets adapted to the models they will train.
• Scientific & engineering leadership: Contribute to publications and client-facing deliverables. Manage compute grant applications and allocations; and engage with HPC support teams, industrial, and academic partners to keep our computational discoveries robust and experimentally grounded. Ensure our scientific workflows are accurately documented.

🤓 Expertise & Skills

• 2+ years of industrial (computational) R&D or large-scale scientific computing or HPC systems experience, with background in Computational Chemistry/Physics, DevOps or IT System Admin work
• Real HPC operational depth — comfortable running jobs across multiple clusters, working with SLURM, remote job submission, GPU builds/benchmarking, and diagnosing job submission issues and bottlenecks.
• Software & data engineering skills — strong Python skills to develop autonomous workflows, experience with databases and storage formats for scientific data (SQL, HDF5/parquet), reliability/recovery tooling, and version control (Git).
• Agentic software skills — use skills and multiple agents to improve the software and documentation you output.
• Strong analytical skills, scientific rigour, and the ability to drive projects independently in a fast-paced startup environment.
• Excellent communication skills in English; ability to present complex results to both technical and non-technical audiences.