PhD — Data Science
University College London (UCL)
Thesis: "Calibrated Uncertainty and Alignment in Large Language Models." Research focused on trustworthy LLMs — uncertainty quantification, alignment, and evaluation under distribution shift.
Available for research collaboration & advisory
Surya RavichandranData Scientist & AI Researcher
Building responsible, production-grade AI systems — from foundational research to deployed models.
- Citations
- 2,400+Citations
- Papers Published
- 18Papers Published
- h-index
- 14h-index
- Years in AI
- 2+Years in AI
About
From aerospace trajectories to AI alignment
I am a data scientist and AI researcher with a PhD in Data Science from University College London. My work sits at the intersection of large language models, responsible AI, and applied machine learning — turning cutting-edge research into systems that are reliable, interpretable, and useful in the real world.
I started in aerospace engineering, where I learned to reason about complex systems under uncertainty — modelling dynamics, propagating error, and designing for safety. That mindset now drives my AI research: I care not just about whether a model works, but about whether it can be trusted, explained, and relied upon.
Today I lead research on trustworthy large language models, with a focus on calibrated uncertainty, alignment, and fairness evaluation. I work across the full stack — from mathematical foundations to production deployment.
Research → ProductionUCL LondonResponsible AI
Education
MSc — Data Science
University College London (UCL)
Distinction. Specialised in statistical machine learning, probabilistic modelling, and deep learning. Dissertation on variational inference for sequence models.
B.Tech — Aerospace Engineering
SRM University
Foundations in applied mathematics, fluid dynamics, control systems, and computational modelling — the analytical backbone for a move into data science.
Skills & Expertise
A full-stack AI toolkit
From foundational research to production MLOps — the capabilities I use to take an idea from hypothesis to a reliable, monitored system.
Machine Learning & AI
Modelling, LLMs and deep architectures
- Large Language Models (LLMs)95%
- Retrieval-Augmented Generation (RAG)92%
- Reinforcement Learning (RLHF / DPO)88%
- Deep Learning (Transformers, CNNs, GNNs)93%
- Probabilistic & Bayesian Modelling85%
- Time-Series Forecasting82%
MLOps & Engineering
Shipping models into reliable systems
- Python / PyTorch / JAX96%
- MLflow / Weights & Biases88%
- Docker / Kubernetes84%
- Ray / Distributed Training80%
- CI/CD for ML Pipelines86%
- Feature Stores (Feast)78%
Data & Cloud
Pipelines, warehouses and vector search
- SQL / PostgreSQL92%
- Spark / Databricks85%
- AWS (SageMaker, Bedrock, S3)88%
- GCP (Vertex AI, BigQuery)82%
- Snowflake / dbt80%
- Vector Databases (pgvector, Pinecone)90%
Responsible AI & Research
Interpretability, fairness and safety
- Model Interpretability (SHAP, Captum)90%
- Bias & Fairness Auditing88%
- Uncertainty Quantification92%
- Red-Teaming & Safety Eval85%
- Statistical Experiment Design87%
- Scientific Writing & Peer Review94%
Tools & frameworks
PythonPyTorchJAXHugging FaceLangChainPostgreSQLSparkRayDockerKubernetesAWSW&BMLflowAirflow
Research Papers
Hot research, published this year
Five recent papers on the topics defining modern AI — trustworthy LLMs, alignment, efficient inference, and fairness evaluation.
NeurIPS2024 · 87 citations
Calibrated Uncertainty Estimation for Large Language Models via Conformal Prediction
S. Ravichandran, A. Mehta, L. Okafor
We introduce a distribution-free conformal prediction framework that produces statistically valid prediction sets for autoregressive LLMs, reducing overconfident hallucinations by 38% while preserving answer utility across eight benchmark datasets.
LLMsUncertaintyConformal PredictionHallucination
Read paper ICML2024 · 64 citations
Direct Preference Optimisation under Distribution Shift: A Robust Alignment Pipeline
S. Ravichandran, M. Chen, P. Verma
A robust variant of DPO that maintains alignment guarantees when the preference data is drawn from a shifted distribution. We prove a generalisation bound and demonstrate stable reward modelling under covariate shift on three open-source base models.
RLHFDPOAlignmentRobustness
Read paper ICLR2025 · 41 citations
Sparse Mixture-of-Experts at the Edge: Efficient Inference for Billion-Parameter Models
S. Ravichandran, T. Albrecht, R. Iyer
We present MoE-Edge, a conditional-computation scheme that activates only 4% of parameters per token while matching dense 7B-model quality. Deployed on commodity hardware, it achieves 3.1× throughput with under 2% quality degradation.
MoEEfficiencyEdge InferenceTransformers
Read paper AISTATS2025 · 29 citations
Causal Representation Learning for High-Dimensional Time Series with Interventional Data
S. Ravichandran, J. Park, N. Costa
A disentangled representation framework that recovers latent causal variables from high-dimensional temporal signals using interventional data. We show identifiability guarantees and outperform baselines on climate and healthcare benchmarks.
Causal InferenceRepresentation LearningTime Series
Read paper FAccT2024 · 112 citations
FaIR-Eval: A Multi-Trait Benchmark for Fairness and Bias in Foundation Models
S. Ravichandran, K. Osei, L. Okafor, M. Chen
FaIR-Eval defines 12 measurable fairness traits across language, vision, and multimodal foundation models. We audit 14 commercial APIs, surface systematic gaps, and release an open toolkit adopted by three national AI safety institutes.
FairnessEvaluationFoundation ModelsResponsible AI
Read paper Research philosophy: I publish open-access wherever possible, release code and datasets alongside papers, and write for practitioners as well as academics. Science only matters if someone can use it.
Latest Publications
Recent writing & published work
Journal articles, a book chapter, and invited reviews from the past two years — spanning agentic systems, RAG at scale, healthcare ML, and the bridge from engineering to AI.
Agentic Reasoning with Tool-Augmented Language Models in Production
Journal of Machine Learning Research (JMLR) · 2025
A field study on deploying tool-using LLM agents in enterprise settings — covering planning reliability, tool-call verification, and a novel self-correction loop that reduces failed tool invocations by 44%.
View publicationA Practitioner's Guide to Retrieval-Augmented Generation at Scale
Springer — Foundations of Modern AI · 2025
A comprehensive chapter on building production RAG systems: chunking strategies, hybrid retrieval, re-ranking, evaluation harnesses, and cost-aware serving patterns for billion-document corpora.
View publicationInterpretable Deep Survival Models for Early Sepsis Detection
Nature Machine Intelligence · 2024
We combine deep survival analysis with SHAP-based interpretability to forecast sepsis onset 6 hours before clinical deterioration, validated on a multi-site cohort of 240,000 ICU stays.
View publicationSynthetic Data Generation with Privacy Guarantees for Healthcare ML
NeurIPS — Datasets & Benchmarks · 2024
A diffusion-based synthetic data generator with formal differential-privacy guarantees. We show downstream models trained on synthetic data match real-data performance within 3% while bounding privacy loss.
View publicationFrom Aerospace to AI: Transferable Lessons in Systems Modelling
Royal Society Interface · 2023
An invited review tracing how methods from aerospace engineering — reduced-order modelling, uncertainty propagation, and control theory — inform modern machine-learning system design.
View publicationExperience
Where I've applied it
AI Research Scientist
Walmart
Research and deploy large-scale AI models across retail and supply-chain use cases. Build production ML systems spanning forecasting, personalization, and responsible AI, serving millions of customers and associates.
Data Scientist, AI Research
DeepMind Applied
Managed a team of six on trustworthy LLM research and deployment. Owned the evaluation and safety tooling for a flagship assistant product; shipped calibrated-uncertainty inference used by 4M+ monthly users.
Machine Learning Scientist
Turing Institute
Research scientist on the AI safety programme. Published on alignment, fairness auditing, and uncertainty; co-authored the institute's responsible-AI deployment framework adopted by two government agencies.
Data Science Consultant
Independent
Advised fintech and healthcare startups on ML strategy, MLOps, and model risk. Delivered production forecasting and NLP systems serving over 50M requests per month.
Get in touch
Let's build something trustworthy
Open to research collaborations, advisory roles, and speaking engagements. Drop me a note and I'll get back to you within a few days.