Lingamurthy Pokathota
Professional Summary
Forward Deployed Engineer with 15+ years of experience designing, building, and operating data and AI platforms for utilities, financial services, and public-sector clients. Strongly focused on Snowflake-based data platforms, Snowpark Python, and end-to-end GenAI systems using LangChain, Bedrock (Claude), and Cortex AI. Experienced building production RAG pipelines, streaming LLM responses with WebSocket-based UX, and embedding agents that deliver Text-to-SQL and document summarization workflows. Hands-on ownership across architecture, backend APIs (FastAPI/Python), infrastructure as code (CDK), CI/CD (Jenkins → CodeBuild), monitoring, and on-call support. Delivered high-impact results: multi-bot platforms with 500+ daily users, real-time operational dashboards, and governance controls that caught $2M in misreported generation data. Seeking roles that combine applied GenAI, Snowflake platform engineering, and customer-facing delivery.
Technical Skills
Work Experience
- Architected a multi-bot GenAI platform using LangChain and Bedrock to deliver 10 specialized AI bots; designed modular retrieval, prompt templates, and response handlers to enable rapid bot addition.
- Implemented a streaming LLM pipeline (WebSocket → SNS → Lambda → Bedrock → PostToConnection) to bypass API Gateway timeouts and stream tokens to users as they generate.
- Deployed Cortex AI inside Snowflake to run LLM Functions for document summarization and classification; integrated Cortex Search and Cortex Analyst to remove a custom embedding pipeline and save ~60% of manual reporting effort (percentage).
- Built the backend APIs and bot runtimes with FastAPI and Python, and onboarded 500+ daily users to GenAI features through WebSocket streaming (scale).
- Constructed the Snowflake platform architecture including data vault modeling, dynamic tables, streams/tasks for CDC, and Snowpark Python UDFs to push ML scoring into Snowflake; migrated 50+ data assets to the platform (count).
- Authored a three-way comparison engine (Snowflake vs Oracle vs PI Historian) that runs daily to validate generation data and automated stakeholder alerts; discovered and corrected $2M in misreported generation data (money).
- Automated CI/CD with Jenkins pipelines feeding AWS CodeBuild and CDK deployments; implemented auto-backout branches to reduce deployment recovery time.
- Monitored pipeline health with scheduled Python validation scripts and alerting; maintained on-call ownership for data freshness, ETL failures, and GenAI service reliability.
- Led a migration of large datasets from Oracle to cloud-hosted systems, processing multi-million record extracts and full audit trails for state agency integrations (scale).
- Reduced average migration duration by refactoring processes and templates, bringing follow-on agency migrations down from ~3 months to ~5 weeks (time/duration).
- Built a reusable migration framework and orchestration patterns that standardized data validation, error handling, and recovery across agencies.
- Implemented a data quality scoring engine that flagged ~15K integrity issues prior to production cutover and prevented downstream data breaks (count).
- Designed transformation and mapping rules in Informatica and PL/SQL to enforce SCD Type 1/2 logic and ensure zero data loss during cutover.
- Partnered with client stakeholders on acceptance criteria, audit trails, and rollback procedures to satisfy state compliance requirements.
- Rebuilt 30+ Informatica PowerCenter jobs as Snowflake-native ELT, replacing heavy on-prem compute and achieving a 35% infrastructure cost reduction (percentage).
- Refactored orchestration into Python-driven Snowflake Tasks and modular session scripts to simplify maintenance and improve reliability.
- Migrated data movement to Snowflake using a combination of staged loads and DMS for continuous replication where required (count).
- Implemented Snowpark Python UDFs and stored procedures to centralize transformation logic and reduce downstream data movement.
- Automated environment provisioning and schema deployments with CDK and Jenkins pipelines to speed up team onboarding.
- Validated data quality and lineage during migration with reconciliation reports and targeted sampling to ensure parity with on-prem results.
- Migrated Informatica workloads to Snowflake-native ELT patterns, reducing reliance on legacy on-prem tooling and simplifying pipelines.
- Automated data infrastructure provisioning (schemas, warehouses, roles, grants) with scripts to remove manual ticket waits and accelerate onboarding.
- Implemented RBAC, dynamic data masking, and column-level security to meet financial compliance and protect sensitive data.
- Designed and enforced encryption-at-rest and key management practices as part of the governance layer.
- Worked directly with 10+ analytics teams to enable self-service access and trained teams on Snowpark and task-based orchestration (count).
- Authored runbooks and operational playbooks for incident response and data recovery for Snowflake-based workloads.
- Led a 5-person team maintaining 100+ Informatica mappings that processed ~50M records per day for wealth-management reporting (count / scale).
- Architected reusable templates and pushdown optimization patterns in Informatica to accelerate development and improve throughput.
- Directed SCD Type 2 implementations and complex incremental load patterns to preserve historical accuracy in reporting marts.
- Conducted code reviews, capacity planning, and performance tuning for ETL processes to maintain nightly SLA targets.
- Coordinated cross-functional debugging and root-cause analysis for high-severity pipeline failures and restored services under SLA.
- Mentored junior engineers on data modeling, ETL best practices, and production support processes.
Education
Certifications
Powered by Drivetube · Create your own profile at drivetube.ai
Everything on Drivetube
Six products, two of them free forever. Start wherever you are.
Your free digital resume
at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept.
Documentation- Free Job BoardFree
Verified jobs, posted in the last 3 days
verified openings crawled ATS-by-ATS from 140,000+ real company career pages across 50+ ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed.
Documentation - Resume Writing ServicesFrom $25.99
Written by senior career writers
human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile.
Documentation - Drivetube OneFrom $39.99 / 3 mo
Daily matched jobs, tailored resumes, or we apply for you
Drivetube's paid service. Community sends daily Jobsheets of fresh jobs matched to your profile on WhatsApp and email, with the Drivetube Community ($39.99 for 3 months or $69.99 for 6 months; ₹999 or ₹1,899 in India). Jobhunt is one-time application credits with Community included: one credit tailors one resume and its cover letter (100 for $99 with 3 months of Community, 250 for $199 with 6 months). Let Us Apply is an add-on to Jobhunt: a human expert applies 250 times for you on your credits ($0.60 each, $150). Everything lives on one dashboard at drivetube.ai/drivetubeone.
Documentation - Drivetube HireFree tier
For employers — no job postings, no applications
hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do.
Documentation
- Documentation
every product explained in full, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.
- Playbooks
tactical job-search guides. Each post is one named tactic with the situation it applies to, the exact steps, a copy-paste message and honest failure modes. Free, no account.
The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.
Pricing is identical on the web, iOS and Android — no app-store markup. Monthly Community membership is purchased in the iOS app only; the website sells annual plans. The Android app has no in-app purchase, so Android members subscribe on drivetube.ai and then sign in to the app with full access. Membership follows your account, not your device.