Sricharan muralidharan

As an AI/ML Engineer, I am driven by a determination to achieve mastery, taking full accountability for delivering precise and impactful solutions. I thrive on the autonomy to independently architect and implement highly logical, structured systems that solve complex challenges.

Experience

AI/ML Engineer

Tiger Analytics · Jan 2026 – Present

Not yet confirmed

• Insights Pro – Agentic Analytics Platform
• • Implemented a hierarchical multi-agent architecture with a central orchestrator that routes queries to specialized agents for task-specific execution.
• • Designed RAG and web search agents to augment the orchestrator with relevant context, enabling more accurate planning and execution.
• • Developed dynamic schema filtering to provide the LLM with only relevant tables and columns, reducing noise and improving SQL generation.
• • Implemented real-time streaming for node-level outputs, cutting user-perceived latency by 60%.
• • Developed a knowledge base caching mechanism to reduce redundant LLM calls, improving throughput and lowering inference costs.
• • Assited in evaluation workflows using heuristic validation and automated LLM testing to ensure output consistency.
• Data Science Agents – Multi-Agent AI Platform
• • Worked on multi-agent LLM systems for data science workflows, enabling task decomposition across EDA, ETL, and modeling stages.
• • Improved agent coordination and response quality by refining prompt structures and intermediate context handling across multi-step workflows.
• • Implemented strategies for managing intermediate artifacts (datasets, analysis outputs) outside LLM context to improve scalability and reduce token usage.
• • Analyzed failure cases in multi-agent execution flows and iteratively improved system robustness and output consistency.

AI/ML Engineer

Tiger Analytics · Jan 2024 – Present

Not yet confirmed

• Architected a hierarchical multi-agent query resolution system with a Router/Orchestrator agent that classifies incoming queries as simple or complex, triggering lightweight or full multi-agent execution pipelines to optimize cost and response latency.
• Built RAG and web-search agents using pgvector for production vector storage and semantic retrieval (with ChromaDB/Qdrant supported for alternate deployments), with optimized embedding strategies to improve context relevance for orchestrator planning.
• Developed dynamic schema-filtering to inject only relevant tables/columns into the LLM context, reducing noise and improving SQL generation accuracy.
• Engineered real-time streaming for node-level response delivery and a Knowledge Base caching layer to cut redundant LLM calls, reducing user-perceived latency by 60% and lowering inference costs.
• Developed an automated evaluation framework for the SQL agent using an LLM-as-judge approach, ensuring consistent output quality at scale.
• Built LLM tool-calling infrastructure for automated scikit-learn model building and fine-tuning, enabling the agent to select the correct modeling tool and arguments and execute the full train/tune cycle autonomously.
• Designed and implemented a human-in-the-loop feedback system end-to-end, allowing users to steer agent execution mid-run; feedback dynamically revises the plan and is routed to the relevant downstream agent.
• Implemented strategies for managing intermediate artifacts (datasets, analysis outputs) outside LLM context to improve scalability and reduce token usage.
• Deployed the multi-agent platform on AWS using ECS Fargate and ECR for containerized, serverless orchestration of agent workloads.
• Evaluated DeepAgents as an alternative orchestration layer, benchmarking token consumption and inference cost against the LangChain/LangGraph stack and reverting based on quantitative analysis.
• Improved factual reliability of an existing RAG-based research chatbot by replacing hybrid BM25 + RRF retrieval with cross-encoder reranking, achieving the project's highest recorded citation accuracy and raising faithfulness by 27 percentage points (0.31 to 0.58) on a 90-query, 9-workflow evaluation benchmark.
• Engineered a bi-directional factual-contradiction guard to catch and fail LLM outputs that contradict retrieved source data, directly driving the faithfulness gains above.

Senior Data Analyst

Tiger Analytics · Jan 2025 – Mar 2026

Not yet confirmed

Data Analyst

Tiger Analytics · Feb 2024 – Jan 2025

Not yet confirmed

Associate Software Engineer

BNP Paribas · Jul 2023 – Dec 2023

Not yet confirmed

• Centric – E-banking Platform
• • Enterprise Automation: Engineered and maintained mission-critical CI/CD pipelines using Jenkins and Ansible, reducing manual deployment errors and accelerating release cycles.
• • System Resilience: Collaborated with infrastructure teams to optimize high-availability financial systems, ensuring 99.9% uptime through containerized deployments and proactive monitoring.
• • Infrastructure as Code: Streamlined resource provisioning and configuration management, integrating DevOps best practices into large-scale banking platforms.

Associate Software Developer

BNP Paribas · Feb 2023 – Dec 2023

Not yet confirmed

• Built CI/CD pipelines (Jenkins, Ansible) and automated infrastructure provisioning for a Tier-1 bank.

Intern

BNP Paribas · Feb 2023 – Jul 2023

Not yet confirmed

• • Gained hands-on proficiency in Continuous Integration (CI) and Deployment (CD) automation within a Tier-1 financial environment.
• • Developed automation scripts using Ansible to streamline routine operational tasks and supported the execution of automated build pipelines via Jenkins.

Learner

Coding Club · May 2020 – Mar 2023

Not yet confirmed

What drives their work

The Architect

They meticulously design the underlying structure before bringing a system to life.

Sricharan's superpower

You excel at designing and implementing complex, resilient systems that deliver measurable improvements.

How Sricharan works

You would excel in teams focused on building robust, high-performance, and scalable technical infrastructure, particularly in AI/ML or platform engineering.