Lead Data Scientist

Roles & Responsibilities

As a Lead Data Scientist, you will:

• Own technical charters and roadmap for multiple ML/CV initiatives.
• Lead and mentor applied scientists, mapping complex EO problems into actionable, scalable decision systems.
• Drive hypothesis generation, experimentation, architecture design, model development, and deployment for production ML pipelines.
• Own E2E delivery of large-scale ML/CV systems - from problem framing to data design, model development, deployment, and monitoring.
• Collaborate with Product, MLOps, Platform, and Geospatial experts to convert ambiguous requirements into elegant solutions.
• Communicate technical findings to leadership, customers, and cross-functional partners with clarity and precision.
• Assist in effective project, resource management, and timely deliverables (in an agile manner), via showcasing strong sense of ownership and accountability.
• Build reliable, efficient models that scale across geographies, seasons, sensors, and business domains.
• Write clean, scalable production-grade code in Python/PyTorch.
• Conduct A/B experiments and calibrate ML metrics to business KPIs.
• Innovate on model architectures (Transformers, diffusion, generative, time-series models, self-supervision, multimodal fusion and temporal modeling) to advance in-house geospatial ML SOTA.
• Represent your work through patents, technical documents, internal whitepapers, and publications (as applicable).
• Contribute to hiring and technical excellence, including mentoring junior team members and interns.

Required Qualifications

Education

• PhD/M.Tech/MS (Research) in CS, EE, EC, Remote Sensing, or related fields preferably from leading academic/industrial labs/institutes/corporates.
• Exceptional undergraduates with strong research/industry experience will also be considered.

Experience

• 6+ years of applied ML/Computer Vision experience (industry preferred).
• 2+ years in a technical leadership role - people and project leadership.
• Proven experience taking ML models from POC → production → monitoring.

Must-have Technical Expertise

To be eligible for this role, we are looking for candidates with the following qualifications:

• A proven track record of relevant experience in computer vision, NLP, learning theory, optimization, ML+Systems, foundational models, etc.
• Technically familiar with some, or most of (as evidenced by problem solving skills in novel scenarios): Transformers, UNet, RNNs/LSTMs/GRUs, YOLO/RCNN/Encoder–Decoder architectures, Generative models (GAN, VAE, Diffusion), Self-supervised & contrastive learning, Representation learning, domain adaptation & generalization, Semi-/Active learning, noisy-label learning, Super-resolution, anomaly detection, clustering, Model compression: distillation, pruning, quantization.
• PyTorch, Python, SQL, distributed systems (Spark), MLOps for large-scale training, data pipelines, and deployment.

Good to have

• SAR (VV/VH), NDVI, FCC, multispectral optical data, Temporal modeling (SITS, forecasting, seasonal dynamics), Cross-modal fusion (SAR+Optical, EO+tabular/ground)
• First-authored publications in ICLR, NeurIPS, CVPR, ICCV, ECCV, ICML, AAAI, IGARSS, IEEE TGRS, etc.
• Experience with geospatial datasets, climate models, foundation models, or EO analytics.

Benefits:

• Medical Health Cover for you and your family including unlimited online doctor consultations
• Access to mental health experts for you and your family
• Dedicated allowances for learning and skill development
• Comprehensive leave policy with casual leaves, paid leaves, marriage leaves, bereavement leaves

Interview Process:

• Intro call
• Assessment
• Presentation
• Interview rounds (ideally up to 3-4 rounds)
• Culture Round / HR round