App LogoApp name
SG

Sahil Gaikwad

Open to work2 years experience

Software Engineer

Mumbai, IndiaTarget Roles: Backend Engineer • Full-Stack Developer • Frontend Specialist

Associate Software Engineer specializing in AI/ML and Backend Development.

GitHub

Standing Rank

Rank Not Available

Developer Badges

No badges earned yet

Skills & Technologies

59 skills
pythonjavac++javascriptsqldjango rest frameworkdjangofastapiflaskcelerypytorchtensorflow/keraswebhookvision-language models (vlm)retrieval-augmented generation (rag)cnnyoloqlora fine-tuningprompt engineeringlangchainollamascikit-learnopencvtesseract ocrgoogle vision apimatplotlibdashpostgresqlmysqlredisrabbitmqfirebaselambdaec2s3api gatewaybedrockbedrock knowledge basedynamodbsqssnstextractvpcecriamcodebuildazure ai foundryhtml5css3tailwind cssbootstrapmaterial uiangularjsxamppdockerjenkinsgitseleniummatlab

Work Experience

Associate Software Engineer

GMoney Pvt. Ltd.

Sep 2024 - Present Mumbai, India
  • Claim Tracker:Automated claim-status retrieval across 15+ insurance/TPA portals by reverse-engineering network flows and building custom authentication adapters, processing 2,400+ daily retrievals at 70% end-to-end automation.
  • Reduced batch retrieval latency to under 30 seconds for 1,200+ records per run via cron-triggered Celery tasks with randomized invocation windows and streamlined session lifecycle management.
  • HSP Bill Audit:Built a vision-language model pipeline extracting structured data from unstructured hospital bills with 85–90% accuracy across 10,000+ formats; applied QLoRA fine-tuning (0.6% of parameters on 50 samples) with targeted preprocessing, improving accuracy by 15–20%.
  • Migrated inference from self-hosted Qwen 7B (EC2 GPU) to AWS Bedrock (Qwen 22B), improving output quality and reducing compute costs by 60% with zero manual intervention.
  • OPD Bill Audit:Delivered an AI-powered handwritten prescription extraction system processing 100–300 OPD bills/day with 15–30s asynchronous turnaround; integrated a RAG-grounded correction layer via Bedrock Knowledge Base to resolve doctor shorthand into canonical medicine names.
  • Deployed Qwen VLM (Mixture-of-Experts) via AWS Bedrock – leveraging sparse expert activation for efficient multi-format inference – backed by a fully asynchronous DRF pipeline (Celery, RabbitMQ, Redis), decoupling API response from model latency with PostgreSQL persistence.
  • Document Validation:Designed and shipped a compliance-ready serverless document validation system processing 500+ documents/day across 9 document types at sub-10s turnaround and 90% accuracy; integrated a YOLO-based logo classifier and PII redaction pipeline (Aadhaar/PAN), reducing manual reviews by 80%.
  • Signature Verification:Developed an ensemble signature verification system combining a Siamese CNN with OCR-based text matching; slashed false-positive rate from 35% to under 5% via ensemble scoring, achieving 97% accuracy on PAN-to-disbursement signature verification.
  • Improved model robustness through six-fold data augmentation and F1-optimized precision-recall threshold tuning on 100 signature pairs.
  • Claim Desk:Enhanced a live insurance claims platform over 150,000+ records to 700ms–1s dashboard response via ORM query optimization and asynchronous concurrent processing; implemented Autonomous policy decoding (co-pay, subvention, coverage terms) with bidirectional MEAN server sync, eliminating manual document handoffs.
  • DPD:Shipped a loan recovery module with dynamic payment link generation (Razorpay, Cashfree), WhatsApp integration, WebSocket-based agent call scheduling, and nightly LMS sync – reducing recovery turnaround by 40%.

Software Engineering Intern

Acuradyne Systems

Jun 2024 - Aug 2024 IIT Bombay [ SINE ], India
  • Maintained 2 Ai-enabled IoT healthcare diagnostic systems through active clinical trials, debugging FastAPI services and EC2 infrastructure; engineered Lambda Layers via Docker to resolve a critical Firebase connectivity gap in a serverless backend.

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

Achievements Not Earned

Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.

About Details

Professional Bio

Associate Software Engineer with expertise in AI/ML, backend development, and cloud infrastructure. Proven track record in automating complex workflows, optimizing system performance, and deploying scalable AI solutions using AWS, Python, and Django.

B.E. Information Technology, Honors in Data Science in Information Technology

University of Mumbai ( - 2024)

Languages: English, Hindi
Sahil Gaikwad - Profile | Swiftcruit