AI Engineer with less than a year in multi-agent systems and LLM orchestration
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI engineer specialising in multi-agent systems, LLM orchestration, and Model Context Protocol (MCP) integrations - building production pipelines where agents plan, self-correct, and evaluate regressions autonomously. Shipped a self-improving prompt optimization engine alongside a 5-agent GTM intelligence system with critic-driven retry loops. Experienced in RAG pipelines, LangGraph workflows, semantic search, vector databases, and FastAPI deployments on Amazon Web Services (AWS) and Microsoft Azure.
Uttarakhand Technical University
Bachelor of Technology · Computer Science and Engineering
N/A – June 30, 2026
GTM Intelligence
June 24, 2026 – Present
Built a 5-agent pipeline featuring a critic loop that evaluates outputs via claim-level PASS|RETRY|FAIL verdicts; the planner dynamically alters search strategies and industry filters across up to 3 autonomous retry cycles. Integrated Anthropic MCP servers to securely call live Gmail and Google Drive contexts; isolated tool exceptions within independent fault circuits to preserve core runtime stability during external API degradation. Designed a multi-factor ICP scoring engine and real-time streaming architecture via FastAPI WebSockets to feed live agent state, confidence meters, and timeline intervals to a React frontend; unified deployment on Render.
View ProjectNetwork Security System
June 24, 2026 – Present
Architected an ML pipeline (ingestion, KNN imputation, training, S3 sync) on 11,055 samples featuring KS-2 statistical drift detection, lifting classification F1 score to 97.65% via automated GridSearchCV tuning across 5 models. Containerized the architecture with Docker and deployed a FastAPI REST service backed by a fully automated GitHub Actions CI/CD workflow that syncs verified production artifacts into Amazon S3 storage buckets.
View ProjectBrand Guardian AI
June 24, 2026 – Present
Automated video compliance auditing via a LangGraph DAG running at ~128s/video, utilizing LangSmith tracing to isolate total AI computation latency to under 11 seconds (averaging $0.003/run). Designed a RAG pipeline leveraging Azure OpenAI Embeddings and Azure AI Search top-3 cosine retrieval to ground all GPT-40 decision criteria in real-time regulatory compliance rulebooks rather than raw model weights.
View ProjectCultural Fit Analysis
The candidate's projects demonstrate a strong initiative and self-driven learning, as all listed projects are personal. The diversity of projects (GTM Intelligence, Network Security, Brand Guardian AI) shows a broad interest in applying AI across different domains. The use of modern tools and frameworks (LangGraph, FastAPI, React, Docker, AWS, Azure) indicates a proactive approach to adopting new technologies, which is a good fit for an innovative culture. The candidate is still pursuing a Bachelor's degree, which might indicate a need for mentorship and structured guidance in a professional setting.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a strong problem-solving aptitude and an ability to design complex, resilient systems (e.g., fault circuits, dynamic retry cycles). The focus on optimizing latency and cost (Brand Guardian AI) suggests an operational mindset. However, without direct interview data, soft skills like teamwork, leadership, and adaptability cannot be fully assessed.