Scientist (AI Modeling for Computational Sciences)

Join us and contribute to the discovery of medicines that will impact lives
Hyderabad, India | Hybrid | Full-Time
About Aganitha

High-throughput experimentation, computational & data-driven modeling, and the advent of the Open Science era are fundamentally transforming research, discovery, and development across diverse industries. Aganitha is at the forefront of co-innovation with global clients, shaping next-generation R&D ). While our primary client base has been in global Biopharma, we are actively expanding our collaborations into consumer brands and, in the near future, the materials design industry.

As a Scientist at Aganitha, you will be instrumental in leveraging cutting-edge advances in computational chemistry, materials science, soft matter physics, AI/ML, and high-performance computing in the Cloud. You will contribute to accelerating design and development across a spectrum of applications, including but not limited to: small molecule therapeutics, biologics, gene, cell & RNA therapies within Biopharma; new product formulations for consumer brands; and novel materials for various industrial applications.

You will collaborate closely with research leaders at our client organizations, identifying their needs and designing innovative solutions. Working with our internal technical and scientific teams, you will drive solutions from concept to launch and growth. You may also interact with external vendors to coordinate experimental validation of the in silico solutions developed at Aganitha.

To excel in this role, you must possess a strong interest in engaging with customers to apply the latest scientific and technological advancements for R&D acceleration, thereby contributing to Aganitha's growth.

Key Responsibilities

• Design and develop AI/ML models to solve complex problems, such as predicting molecular properties, material behaviors, or reaction outcomes.
• Develop and apply in silico methods to design and optimize therapeutic candidates, including antibodies, RNA molecules, and viral vectors, and leverage bioinformatics tools, biological databases, and AI/ML approaches for biological data analysis and predictive modeling.
• Curate, process, and analyze scientific datasets from various sources, including literature and experimental data, ensuring data quality and readiness for model training.
• Develop intelligent featurization strategies that accurately represent chemical structures, physical properties, or biological interactions, drawing upon your scientific understanding.
• Implement, train, and evaluate cutting-edge Machine Learning and Deep Learning algorithms (e.g., CNNs, RNNs, LSTMs, Transformer architectures) to build robust predictive models.
• Rigorously validate models against client-provided data and established benchmarks, ensuring their accuracy, generalizability, and utility.
• Translate complex technical and scientific findings into clear, actionable insights for both technical and non-technical stakeholders.
• Collaborate effectively with computational chemists, data scientists, and wet lab scientists to define project requirements, iterate on solutions, and ensure successful deployment.
• Stay abreast of the latest advancements in AI/ML, computational chemistry, and relevant scientific domains, continuously seeking opportunities to apply new methodologies.

Qualifications

• The candidate should be skilled in analyzing high-throughput omics datasets such as single-cell, spatial, and genomic data, and in computational modeling of biological systems, including network and pathway analysis. They should also have expertise in the in-silico design and optimization of therapeutic candidates such as antibodies, RNA molecules, and viral vectors. Proficiency in bioinformatics tools, biological databases, and the application of AI/ML approaches for biological data analysis and predictive modeling is essential.
• PhD, post-doctoral research, or equivalent higher studies in Computational Chemistry, Cheminformatics, Materials Science, Chemical Engineering, Biochemistry, Computational Biology, Bioinformatics, Computational Physics, Medicinal Chemistry, Applied Mathematics, Applied Statistics, Fluid Dynamics or a closely related scientific discipline.
• Familiarity with one or more of the following core domain skills: High-throughput docking and QSAR studies, Atomistic or Coarse-grained Molecular Dynamics (including Enhanced MD using PLUMED, Langevin Dynamics, Brownian Dynamics, and Dissipative Particle Dynamics), Periodic or non-periodic Quantum Chemical Calculations, Ab initio MD simulations and QM/MM simulations, Cheminformatics using RDKit, Mathematical Modeling, or Computational Fluid Dynamics.
• Strong foundational understanding of the scientific principles underlying computational chemistry, materials science, or related fields (e.g., colloidal chemistry, polymer science, surfactant chemistry, soft condensed matter physics, etc.).
• Solid mathematical intuition of Machine Learning algorithms, including Deep Learning architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), LSTMs, and Transformer architectures.
• Proficiency in modular, typed, and object-oriented Python programming.
• A high-level understanding of the ML/DL project lifecycle, from data preparation and feature engineering through model development, training, evaluation, and deployment.
• Excellent problem-solving skills and the ability to apply critical thinking to complex scientific and technical challenges.
• Strong verbal and written communication skills, with the ability to effectively communicate technical concepts to diverse audiences.

Nice to Have

• Experience in effectively building and deploying ML solutions using popular frameworks such as PyTorch, TensorFlow, Keras, or scikit-learn.
• Proficiency in shell scripting.
• Proficiency in working with Linux-based operating systems (e.g., Ubuntu, Fedora, CentOS, Debian).

Big Plus

• Exposure to large language models (LLMs) such as ChatGPT, Claude, or Gemini, and practical experience in utilizing such tools for day-to-day work (e.g., writing research reports, understanding new concepts, generating code).
• Experience in optimal usage of High Performance Computing (HPC) resources.
• Familiarity with container-based usage of software and their dependencies (e.g., Docker).

---