Research Scientist, Agentic AI for Closed-Loop Scientific Discovery (Founding Team)

Thermia is the first AI-native solution vertically built for the industrial thermal chain, discovering breakthrough fluids and co-optimizing associated device, from Molecules to industrial systems.

We are a team of machine learning scientists, computational chemists, and thermal engineers united by a single ambition: to create a fundamentally new way of designing the fluids and systems that move heat through our modern economy.

Today's approach to thermal fluid and system design is fragmented, slow, and structurally incompatible with the urgency of the energy transition. Chemists develop fluids without knowledge of the systems they will run in. Engineers design thermal hardware without optimizing the working fluid. The result is decades of R&D, billions in cost and solutions that are sub-optimal by construction.

Thermia replaces this fragmented process with an integrated, physics-grounded discovery pipeline: AI accelerates what human expertise makes possible, and experiments validate what AI generates. Our platform generates entirely novel molecular candidates and co-optimizes the thermal systems associated with each discovery, building a proprietary portfolio of qualified molecules, fine-tuned models, and experimental data with every engagement.

Our work is powering the thermal infrastructure the energy transition cannot wait for.

Place: Paris, France. Level: Entry level, Contract: Permanent, Mode: Hybrid

Snapshot We're looking for a research scientist to help  build agentic systems for closed-loop scientific discovery with autonomous agents that hypothesize, plan, ground, and act across long horizons to discover new thermal materials.

The Role As a Research Scientist on this team, you will design and build the autonomous scientific agents that drive Thermia's closed-loop discovery. You will engineer how they read the literature, ground their reasoning in evidence, plan over long horizons, call the right tools at the right time, and turn results into actionable scientific insight. You will work at the frontier of agentic AI for science, implementing code, running experiments, and owning results end-to-end.

Your work may involve:

• Designing closed-loop agentic discovery systems that iterate between hypothesis, planning, tool use, observation, and refinement

• Engineering long-horizon agents: planning, memory, context management, and recovery across runs that span hours to days

• Building scientific tooling for agents (computational chemistry tools, simulation engines, property predictors, literature and patent search) and the protocols by which agents call them

• Implementing grounded reasoning over scientific literature, turning papers, patents, and databases into structured, citeable evidence that anchors agent hypotheses

• Building evaluation harnesses for agent reliability, factuality, and scientific value including designing benchmarks where simple QA metrics fall short

• Working with multimodal LLMs to parse molecular structures, figures, tables, and reaction schemes from scientific documents

• Designing and maintaining the molecular knowledge base and multimodal retrieval systems that grounds agent outputs

• Analyzing agent trajectories carefully, including debugging, failure analysis, and red-teaming

• Communicating results clearly through plots, writeups, and paper-ready figures

About You

• PhD in Machine Learning, NLP, or a related field or equivalent experience.

• A research track record in LLM agents, scientific ML, multimodal ML, or scientific NLP, including peer-reviewed publications

• Strong implementation ability and comfort in research codebases (Python; PyTorch or JAX)

• Familiarity with the closed-loop agentic discovery literature (e.g. ChemCrow, Coscientist) and current frontier work on long-horizon agents

• Experience with LLM APIs, RAG, tool use, and agent frameworks (LangGraph, LlamaIndex, or similar)

• Strong communication and a bias toward clarity and honesty regarding results

• High agency: you push projects forward and take initiative

In addition, the following would be an advantage:

• Prior project, internship, or PhD work in drug or material discovery

• PhD work on LLM agents, tool-augmented reasoning, multimodal scientific ML, or scientific knowledge bases

• Experience engineering long-running agents (planning, memory, context management, failure recovery)

• Experience building scientific evaluation benchmarks for agentic systems