Satsure·4 months ago
4 months ago
Senior ML Researcher – Foundation Models
Sign up free to see how well your resume matches this role.
What you'll do
- Design and implement self-supervised learning (SSL) objectives tailored for geospatial data
- Develop multi-modal representations spanning optical, SAR, elevation, and derived signals
- Ensure representations transfer effectively across tasks such as segmentation, classification, and change detection
- Design evaluation strategies to measure generalization across geographies, sensors, and time
- Design and scale models based on Vision Transformers (ViT), hybrid architectures, or State Space Models to large parameter regimes
- Apply modern training techniques such as RMSNorm, FlashAttention, mixed precision, and gradient checkpointing
- Run scaling experiments, ablations, and architecture explorations grounded in empirical rigor
- Leverage insights from scaling behavior to make compute-efficient decisions across model size, data, and training strategy
- Develop methods to model time-series satellite data
- Explore sequence modeling, memory mechanisms, and temporal tokenization strategies
- Design ML systems as end-to-end pipelines
- Make explicit trade-offs between model quality, latency, cost, and data freshness
What they're looking for
- 5–8 years of experience in ML research or applied research roles
- Experience in large-scale foundation model development (vision, multimodal, speech, or related domains)
- Experience training and/or fine-tuning billion-parameter models
- Experience working with sequence, video, or temporal data
- Expert-level proficiency in PyTorch or JAX
- Strong experience with Distributed training (FSDP / DeepSpeed)
- Strong experience with Large-scale datasets and training pipelines
- Familiarity with transformer architectures and training dynamics
Nice to have
- Exposure to geospatial foundation models such as Prithvi, Clay, Segment Anything Model (SAM)
- CUDA / performance optimization experience
- Familiarity with efficient scaling techniques (e.g., Mixture of Experts)
- Strong experimental rigor and ability to design meaningful ablations
- Track record of publishing or contributing to state-of-the-art research in representation learning or generative modeling
Summarised by NextRaise from the employer’s description, which follows in full below.
Full description from employer
About SatSure
SatSure is a deep-tech decision intelligence company operating at the nexus of agriculture, infrastructure, and climate action. We turn earth observation data into actionable insights for governments, financial institutions, and enterprises across the developing world — at scale, with reliability.
Role
You will be the architect of the model’s latent space, designing foundation models for multi-spectral, multi-temporal, and multi-resolution geospatial data.
This is a hands-on role involving prototyping, experimentation, and large-scale training. You will work across representation learning, model scaling, and spatiotemporal modeling to build systems that generalize across sensors, geographies, and time.
Responsibilities
Representation Learning
- Design and implement self-supervised learning (SSL) objectives (e.g., Masked Autoencoders, DINO-style methods, contrastive learning) tailored for geospatial data
- Develop multi-modal representations spanning optical, SAR, elevation, and derived signals
- Ensure representations transfer effectively across tasks such as segmentation, classification, and change detection
- Design evaluation strategies to measure generalization across geographies, sensors, and time
Model Development & Scaling
- Design and scale models based on Vision Transformers (ViT), hybrid architectures, or State Space Models (e.g., Mamba) to large parameter regimes
- Apply modern training techniques such as RMSNorm, FlashAttention, mixed precision, and gradient checkpointing
- Run scaling experiments, ablations, and architecture explorations grounded in empirical rigor
- Leverage insights from scaling behavior to make compute-efficient decisions across model size, data, and training strategy
Temporal Dynamics
- Develop methods to model time-series satellite data, capturing:
- Seasonal patterns
- Temporal dependencies
- Long-term land-use changes
- Explore sequence modeling, memory mechanisms, and temporal tokenization strategies
Systems-Level Thinking
- Design ML systems as end-to-end pipelines (data ingestion → curation → training → evaluation → deployment → feedback)
- Make explicit trade-offs between model quality, latency, cost, and data freshness
- Work with platform teams to optimize:
- Distributed training (FSDP, DeepSpeed)
- GPU utilization
- Data pipelines and experiment throughput
- Build reusable components and abstractions, not one-off models
Preferred Background
Experience
- 5–8 years of experience in ML research or applied research roles
- Experience in large-scale foundation model development (vision, multimodal, speech, or related domains)
- Experience training and/or fine-tuning billion-parameter models
- Experience working with sequence, video, or temporal data
- Exposure to geospatial foundation models such as:
- Prithvi
- Clay
- Segment Anything Model (SAM) (nice to have)
Technical Skills
- Expert-level proficiency in PyTorch or JAX
- Strong experience with:
- Distributed training (FSDP / DeepSpeed)
- Large-scale datasets and training pipelines
- Familiarity with transformer architectures and training dynamics
- Bonus: CUDA / performance optimization experience
Additional Strengths
- Familiarity with efficient scaling techniques (e.g., Mixture of Experts) is a plus
- Strong experimental rigor and ability to design meaningful ablations
- Track record of publishing or contributing to state-of-the-art research in representation learning or generative modeling
Company
Satsure
Bengaluru, India
Company facts come from this company's own listings. We only show what the postings themselves carry.