Position Summary
As a Quantum Chemistry Intern, you will work at the intersection of quantum chemistry, computational chemistry, quantum computing, and AI/ML to accelerate molecular modelling, drug discovery, and materials simulation workflows on next-generation quantum and hybrid quantum-classical platforms built at QpiAI. You will contribute to R&D, algorithm development, benchmark creation, workflow automation, and integration of chemistry engines into the QpiAI quantum stack (classical + quantum).
Key Responsibilities
1. Quantum & Computational Chemistry
- Build, simulate, and analyze molecular systems using ab-initio, DFT, semi-empirical, and post-HF methods.
- Prepare & run workflows for tasks such as:
- Geometry optimization
- Frequency calculations
- Single-point energies
- Conformer search
- PES scans (bond, angle, torsion, R-PES)
- Interaction energies
- Benchmark chemical properties across classical software (PySCF, ORCA, Psi4, NWChem, CP2K).
- Assist in developing molecular datasets and automated pipelines for high-throughput computational studies.
- Work in the domain of embedding, projection based methodologies, QM/MM and their transferability to Quantum computing domain.
- Work on advanced methodologies, including:
- Embedding and projection-based techniques
- QM/MM (Quantum Mechanics/Molecular Mechanics) approaches
- Investigate the transferability and application of these advanced methodologies to the domain of Quantum Computing.
2. Quantum Computing for Chemistry
- Convert molecular Hamiltonians into qubit representations using Jordan-Wigner, Bravyi-Kitaev, Parity mapping, and others.
- Work on algorithms such as VQE, QITE, QPE, SQD and hybrid variational solvers.
- Build circuits and anstze that run efficiently on QPUs and simulators.
- Perform quantum resource estimation (qubit count, depth, error budgets).
- Explore quantum-inspired chemical simulation (tensor networks, low-rank factorizations, and others).
3. AI/ML for Chemical Modelling
- Build ML models for chemical property prediction (GNNs, equivariant networks, transformers for molecules).
- Work on AI-accelerated tasks such as:
- Geometry optimization with ML surrogates
- ML-based PES generation
- ADMET & physicochemical property prediction
- Reaction prediction & retrosynthesis models.
- Integrate ML models with classical + quantum workflows for hybrid solver stacks.
- Assist in developing machine learning potentials (MLPs) trained on DFT/CC-level data; work includes dataset generation, feature engineering, and model validation. Some ideas about delta - ML will be a plus.
- Contribute to simulation and data preparation for quantum machine learning (QML) models.
4. Software Development & Integration
- Develop clean, reusable Python code for molecular workflows and solver pipelines.
- Integrate computational modules with QpiAI's software stack.
- Implement modular APIs for molecule input, visualization, simulation, and post-processing.
- Experience in running molecular simulations in a high-performance computing environment, version control with Git
- Contribute to documentation, notebooks, examples, and internal demos.
. Research, Experimentation & Reporting
- Conduct literature review on quantum chemistry algorithms, quantum ML, and hybrid workflows.
- Run experiments, record results, and compare classical vs quantum vs ML performance.
- Prepare internal reports, technical notes, and presentation material for R&D discussions.
- Participate in weekly reviews with quantum hardware, algorithms, and AI teams.
Required Skills
Technical Skills
- Strong understanding of quantum chemistry (HF, DFT, MP2, CC, PES, orbital theory).
- Experience with computational chemistry tools (PySCF, ORCA, NWChem, Psi4).
- Strong Python programming with scientific and cheminformatics libraries (NumPy, SciPy, ASE, RDKit).
- Familiarity with quantum computing frameworks.
- Knowledge of ML frameworks (PyTorch/TensorFlow/JAX).
- Understanding of variational algorithms, quantum Hamiltonians, operator mappings.
Domain Knowledge
- Molecular structure, conformers, basis sets, integrals, spin multiplicity.
- Reaction chemistry or drug discovery workflows (bonus).
- Materials properties, band structures, or solid-state methods (bonus).
Soft Skills
- Strong analytical mindset and problem-solving capability.
- Ability to work in a fast-paced, research-oriented environment.
- Excellent communication and documentation discipline.
Preferred Qualifications
- Pursuing M.Tech/M.Sc/PhD in Chemistry, Chemical Engineering, Physics, Quantum Computing, or related fields.
- Prior internships or projects in computational chemistry or quantum algorithms.
- Publications or preprints in computational chemistry, quantum ML, or quantum algorithms.
- Hands-on experience with molecular simulation datasets or ML chemical models.
