Molecule AI
Website:
moleculeai.com
Job details:
About Molecule AI
Molecule AI is building AI-driven infrastructure for drug discovery. Our platform, MoleculeGEN, combines generative models, physics-based simulation, and domain knowledge to accelerate the design of novel therapeutic molecules. We were recently recognized as "Emerging AI-Powered Drug Discovery Platform" (BioSpectrum Asia Excellence Awards 2024).
We're a multidisciplinary team where AI researchers work alongside expert chemists, biologists, and physicists to solve genuinely hard problems at the intersection of computation and life sciences.
The Role
We're seeking a senior AI technical leader to design and build the computational infrastructure that enables efficient drug discovery at scale.
This is a hands-on technical position where you'll architect AI systems, make critical design decisions, and lead implementation by our AI engineering team.
You'll build reusable frameworks and infrastructure that enable efficient computational experimentation across multiple therapeutic programs—the platform layer, not the application layer.
You'll work directly with our chemistry, biology, and physics experts—learning enough domain knowledge to translate scientific requirements into system architectures, while bringing deep AI expertise they don't have.
What We're Building
AI infrastructure for intelligent computational experimentation.
The core challenge: Drug discovery involves searching astronomical chemical spaces (10^60+ possible molecules) to find rare candidates worth testing in the lab. This requires frameworks that can:
- Orchestrate computational experiments efficiently: You have multiple computational methods available—from fast neural network predictions (milliseconds) to rigorous quantum simulations (hours). Each has different costs, speeds, and accuracy guarantees. Build systems that intelligently route billions of candidates through these methods, deciding which experiments to run on which molecules and when.
- Handle uncertainty and validation: Design decision frameworks that know when to trust fast predictions versus when to escalate to expensive rigorous validation. Build calibration systems ensuring cheap surrogate models align with ground truth.
- Navigate multi-objective optimization: Drug candidates must simultaneously satisfy competing objectives—potency, safety, synthesizability, manufacturing cost. Build frameworks that explore trade-offs and help navigate decisions where there's no single "right" answer.
- Learn from feedback: Create systems that improve as experimental results come back from the lab. Design feedback loops where wet-lab validation refines computational models, making future searches more efficient.
The technical reality: Off-the-shelf ML frameworks don't handle these constraints. You'll need to design novel approaches, identify what can be adapted from existing research, and figure out what requires genuine innovation.
The interdisciplinary aspect: You'll collaborate closely with domain experts who understand what makes molecules druggable but may not know what modern AI can do. This means learning enough chemistry/biology to have intelligent technical conversations while teaching domain experts what's computationally feasible and what isn't.
What You'll Do
System Architecture & Design
- Design infrastructure for multi-stage computational workflows
- Make technical decisions about which AI approaches to apply where and why
- Architect systems handling heterogeneous computational methods with different guarantees
- Identify gaps in existing frameworks and design solutions
Technical Leadership
- Guide AI engineering team through architecture reviews and technical discussions
- Evaluate and integrate relevant research (generative models, optimization methods, multi-agent systems)
- Design computational experiments to validate approaches and measure progress
- Analyze results and iterate on system design based on empirical findings
- Own technical outcomes from concept to validated results
Cross-Functional Collaboration (with chemistry/biology/physics experts and AI researchers/engineers)
- Understand scientific constraints and domain requirements from chemistry/biology/physics experts
- Translate between domain language and technical specifications in both directions
- Guide AI team in implementing solutions that respect scientific constraints
- Communicate capabilities and limitations clearly across disciplines
- Build shared understanding through iterative problem-solving
What You Bring
Required
AI/ML Expertise
- Deep understanding of capabilities and trade-offs of modern AI architectures, frameworks, and tools
- Strong grasp of fundamentals: probabilistic modeling, uncertainty quantification, multi-objective optimization
- Experience designing and building complex AI systems (not just training individual models)
- Ability to find, understand, and apply or adapt relevant research appropriately for task at hand
Systems Thinking & Technical Depth
- Experience architecting systems with heterogeneous components
- Understanding of computational cost/latency/accuracy tradeoffs
- Comfortable engaging with code: can review implementations, understand technical decisions, debug issues collaboratively with engineers
- Strong foundations in experiment design, evaluation methodology, and statistical analysis
- Track record shipping complex systems to production or research validation
Collaboration & Learning
- Ability to learn new technical domains quickly
- Clear communication: can explain complex systems to varied audiences
- Intellectual humility: comfortable saying "I don't know" and asking good questions
Education & Experience
- PhD in Computer Science, AI/ML, or related field (or equivalent demonstrated expertise through shipped systems and technical contributions)
- 8+ years building AI/ML systems with increasing technical responsibility
- 3+ years in technical leadership roles (architecture decisions, guiding teams, owning outcomes)
Plus
- Experience with AI for scientific applications (computational biology, materials science, chemistry, physics)
- Background in computational chemistry, molecular modeling, or drug discovery
- Publications in top-tier venues (AI conferences: NeurIPS, ICML, ICLR; domain venues)
- Experience with multi-agent systems, reasoning frameworks, or large-scale optimization
- Familiarity with physics-based simulation methods
What Success Looks Like
In the first year:
- Infrastructure enabling multiple therapeutic programs to run efficiently
- Validated improvements in computational efficiency (candidates evaluated per GPU-hour, quality of lab-tested molecules)
- Strong collaborative relationships with chemistry/biology teams
- Clear technical roadmap for platform evolution
Long-term:
- Platform that demonstrably accelerates drug discovery timelines
- Novel technical contributions (systems, methods, architectures) that advance the field
- Team of AI engineers you've mentored and grown
- Recognition as technical leader in AI for drug discovery
What We Offer
- Work on genuinely novel technical problems at the intersection of AI and life sciences
- Collaborate with world-class experts across AI, chemistry, biology, and physics
- Significant autonomy in technical decision-making and platform direction
- Opportunity to shape infrastructure that could accelerate development of life-saving medicines
- Competitive compensation and equity
- Location: Delhi, India (hybrid/flexible arrangements considered for exceptional candidates)
To Apply
Apply on the Jigya Platform with a brief note in the Cover Letter section explaining:
- A complex AI system you've built: What was the technical challenge? What design decisions did you make and why? What would you do differently now?
- Your approach to learning new domains: How do you get up to speed in unfamiliar technical areas? Give an example.
- Why this role specifically interests you (optional but helpful)
We value demonstrated ability over credentials. If you've built impressive AI systems outside traditional academic paths, we want to hear from you.
Molecule AI is an equal opportunity employer. We value diversity and are committed to creating an inclusive environment for all employees.
Click on Apply to know more.