Gourab Bank
Open to work1 years experienceFull-Stack AI Engineer
Full-Stack AI Engineer building production RAG systems, LLM applications, and distributed backends.
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
23 skillsWork Experience
Full-Stack AI Engineer
Zenziee
- Core engineer on a RAG platform indexing 150K+ freight regulations and carrier contracts; implemented hybrid retrieval (FAISS/pgvector dense search with BM25 re-ranking) serving queries at sub-200ms p99 latency.
- Built the chunking, embedding-generation, and metadata-tagging stages of the document ingestion pipeline, with automated tests covering retrieval and incremental re-indexing on policy updates.
- Developed prompt and agentic-workflow logic for an LLM dispute-resolution assistant that cut average resolution time from 48 hours to under 8 hours.
- Diagnosed a 6-hour Kafka consumer offset lag on a pipeline handling 3M+ weekly shipment-tracking events; resolved it via partition rebalancing and consumer-group tuning.
- Added Grafana dashboards tracking retrieval latency, chunk hit-rate, and LLM token spend.
Software Development Engineer
D&D Motor Systems
- Built a customer-facing service booking portal (React/TypeScript frontend, Java/Spring Boot backend) supporting real-time repair scheduling for 20+ daily technicians.
- Implemented a LangGraph-based workflow that auto-routed incoming repair requests to technician queues, reducing manual processing time by roughly 35%.
- Developed Python/FastAPI microservices for request routing and data writes with 80%+ test coverage, load-tested to sustain 500 RPS at p95 latency under 120ms.
- Contributed to an Airflow ETL pipeline pulling telematics data from 4 vendor APIs into PostgreSQL, helping cut daily pipeline failure rate from 12% to under 1%.
- Helped build a RAG-based internal knowledge assistant over 8 years of service manuals, reducing technician lookup time by about 40%.
Projects
Projects Not Populated
Personal applications, open-source work, and code repos will show here.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Project Helix - LLM Benchmarking & Golden Solutions
Authored golden reference solutions for complex SWE-bench tasks used as ground truth in LLM code-generation benchmarks; built a patch-scoring rubric adopted as the team standard.
Project Escher - Visual Reasoning Evaluation for VLMs
Evaluated charts, diagrams, and real-world scenes to surface VLM failure modes; findings fed into model training data pipelines.
About Details
Professional Bio
Full-Stack AI Engineer with 1.5+ years of experience building production RAG systems, LLM applications, and distributed backends. Expert in Python, FastAPI, Java, Spring Boot, Kafka, and React. M.S. in Computer Science from Syracuse University.
M.S. in Computer Science
Syracuse University (2023 - 2025)
Bachelor of Engineering – Computer Engineering
VESIT, Mumbai University (2019 - Present)