Retrieval & Ranking
Adaptive Retrieval & Specialist Routing
Confidence-gated routing for overlapping retrieval paths with a safe default
Query Routing · BM25 · Semantic Retrieval
PRODUCTION AI · RETRIEVAL · RELIABLE SYSTEMS
Anuraag Mishra
Senior AI/ML Engineer
I build production AI systems across retrieval, routing, grounding, semantic reuse, evaluation, and the backend infrastructure that makes them reliable at scale.
SYSTEM ARCHITECTURE
PRODUCTION AI STACKHybrid RetrievalLexical + Vector
Grounded ContextSource-Aware Retrieval
Continuous EvalFallbacks + Quality Checks
CAREER & EDUCATION
Engineering & Research Journey
Software engineering → graduate AI & optimization research → production GenAI systems.
2017
B.E. Computer Science & Engineering
Panjab University
2017–2022
Software Engineer
Winshuttle (now Precisely)
2025
M.Sc. Data Science
FAU Erlangen-Nürnberg, Germany
2025–Present
Senior Associate — Technology (AI/ML)
Synechron · Goldman Sachs engagement
2017·Panjab University
B.E. Computer Science & Engineering
2017–2022·Winshuttle (now Precisely)
Software Engineer
2025·FAU Erlangen-Nürnberg, Germany
M.Sc. Data Science
2025–Present·Synechron · Goldman Sachs engagement
Senior Associate — Technology (AI/ML)
FLAGSHIP SYSTEMS
Featured AI Systems
Three production AI systems showing how I approach routing, grounded document intelligence, and safe semantic reuse.
Document Intelligence & RAG
Grounded Document Intelligence
Progressive document ingestion and source-grounded AI over user-controlled collections
RAG · Document Intelligence · Semantic Retrieval
AI Reliability & Retrieval
Semantic Cache & Reliability Layer
Precision-first reuse of previous answers and retrieval results
Semantic Caching · Hybrid Retrieval · Query Understanding
PEER-REVIEWED RESEARCH
Featured Applied Research
Neural networks and mathematical optimization for sharper sparse-view tomographic reconstruction.
Machine Learning: Science and Technology · 2025
A compact ReLU network is trained to approximate local edge intensity from image patches, then translated into a mixed-integer formulation and integrated with an optimization-based reconstruction pipeline. The resulting method improves edge sharpness and material homogeneity while preserving explicit control over reconstruction fidelity.
Author contributions
Lead contribution:Software · Investigation · Formal Analysis · Data Curation
Equal contribution:Conceptualization · Methodology · Validation · Visualization · Writing
PUBLISHED BENCHMARK5 Sparse Projections
CSHM Baseline
RME: 0.042
BMS: 0.974
DNN-MIP RO
RME: 0.017
BMS: 0.998
Adapted from Mishra et al., Mach. Learn.: Sci. Technol. (2025) · CC BY 4.0
PROJECTS & LABS
Smaller Systems, Focused Experiments
Compact engineering notes that isolate one useful algorithm, workflow, or evaluation problem at a time.
Ranking & Personalization
Personalized Follow-up Question Ranking
Relevant next questions without repetitive suggestion loops
Document Intelligence
Adaptive Document Partitioning for Vision Models
Finding the largest reliable document segment under model limits
Evaluation & Reliability
Evaluation-Driven AI Workflow Migration
Compare behavior before replacing a working AI workflow
EXPERIENCE
Engineering Experience
Building production AI and distributed backend systems across regulated financial workflows and enterprise software.
Senior Associate — Technology (AI/ML)
Synechron · Goldman Sachs engagement · Bengaluru, India
Building retrieval, grounding, query-intelligence, and reliability layers for GenAI workflows in a regulated financial environment.
- ›Designed hybrid retrieval and routing flows that combine deterministic patterns, lexical search, and semantic retrieval so different query types can take the path best suited to them.
- ›Built query-understanding and reuse layers using semantic caching, entity extraction, and temporal resolution to reduce redundant model work and improve retrieval consistency.
- ›Developed evaluation and fallback mechanisms for retrieval quality, grounding, freshness, and failure handling so production workflows degrade predictably rather than silently.
PythonFastAPIRAG / LLMsVector SearchBM25Evaluation
Software Engineer
Winshuttle (now Precisely) · India
Built backend services and distributed data-processing systems for enterprise SAP automation products.
- ›Developed high-throughput ETL and backend services for processing large volumes of SAP business data across distributed enterprise workflows.
- ›Built fault-tolerant asynchronous processing with RabbitMQ, retries, dead-letter handling, and restartable workflows for long-running operations.
- ›Improved processing and delivery reliability through distributed-service design, CI/CD automation, containerization, and production-focused testing.
C# / .NETJavaNode.jsRabbitMQSQLDistributed SystemsCI/CD
LEADERSHIP & PEER ENDORSEMENTS
Professional Recommendations
Direct endorsements from engineering leadership and cross-functional leads on LinkedIn.
PA
Pallavi Aggarwal
Director of Software Development
Managed Anuraag directly
“Anuraag excelled in taking on complex development tasks, delivering them with impeccable quality, comprehensive unit tests, and thorough integration testing.”
Read full excerpt
“Anuraag excelled in taking on complex development tasks, delivering them with impeccable quality, comprehensive unit tests, and thorough integration testing. His versatility was evident in his ability to handle a diverse range of challenges, from working on legacy VB components to RabbitMQ-based solutions. A standout moment was his involvement in rewriting a legacy license management system into a microservices architecture.”
December 11, 2024
Verified on LinkedInRead recommendation
SM
Shelby Murrell
SAP Functional Lead (Winshuttle/Automate Evolve)
Worked with Anuraag on different teams
“He was not only gifted in technical skills but also in interpersonal skills.”
Read full excerpt
“He was not only gifted in technical skills but also in interpersonal skills. He assisted in making what can typically be a frustrating argument into a clear conversation involving a straightforward resolution. He truly reflects the phrase, 'there is no I in team,' and was always willing to lend his expertise whenever I needed it.”
January 10, 2025
Verified on LinkedInRead recommendation
CORE CAPABILITIES
Technical Capabilities
A working stack across production GenAI, retrieval and ranking, applied machine learning, and distributed backend systems.
GenAI & Agentic Systems
RAG · LLMs · Agentic AI · Prompting · Grounding · Evaluation
Retrieval & Ranking
Embeddings · BM25 · Hybrid Retrieval · OpenSearch · Semantic Caching
ML & Applied Research
PyTorch · Mathematical Optimization · Gurobi · Computer Vision · Experimentation
Backend & Production Systems
Python · FastAPI · REST APIs · Distributed Systems · RabbitMQ · Docker / Kubernetes
ARCHIVE
Earlier Projects & Academic Work
Selected earlier projects, graduate seminars, and preserved technical work.
CONTACT
Let’s talk about production AI systems.
Open to senior AI/ML engineering roles, applied AI work, and technical conversations around retrieval, agents, evaluation, and reliable AI systems.
Based in Bengaluru, India.