Vetted PyTorch Professionals

Akhila Kannegari

Screened

Mid-level AI/ML Engineer specializing in FinTech and retail ML systems

Alabama, USA4y exp

“ML-focused candidate with strong Wells Fargo experience building production fraud systems and internal GenAI tools for fraud analysts. Stands out for measurable impact in fraud detection—raising recall from 71% to 88%—while also demonstrating hands-on depth across streaming infrastructure, MLOps, LLM/RAG implementation, and Python service architecture.”

Naveena Musku

Screened

Mid-level AI/ML Engineer specializing in agentic AI and LLM systems

5y exp

“Backend engineer focused on productionizing LLM systems: built a FastAPI-based RAG and multi-agent automation platform deployed with Docker/Kubernetes, prioritizing safe execution and reduced hallucinations. Experienced in refactoring monolithic ML services with feature-flagged incremental rollouts, and implementing JWT/RBAC plus row-level security (e.g., Supabase) for secure, scalable APIs.”

Kunal Mahato

Screened

Mid-level Software Engineer specializing in AI, full-stack systems, and platform engineering

Virginia, USA6y exp

“Full-stack/AI engineer with experience spanning supply-chain product deployments, biomedical agentic search, and research-grade RAG evaluation. Stands out for owning customer-facing migrations at scale (including 216,000 historical shipments), building measurable LLM systems, and pairing AI experimentation with rigorous evals, rollout controls, and auditability.”

Sharath Amula

Screened

Junior Software Engineer specializing in AI and FinTech

Dallas, TX2y exp

“Frontend engineer with experience in both healthcare and financial services, building high-stakes production interfaces such as AI-powered clinician care planning workflows and real-time fraud investigation dashboards. Stands out for combining React/TypeScript performance optimization with strong UX thinking in regulated, data-dense environments.”

“AI/full-stack product engineer with experience shipping agentic systems in both fintech and enterprise compliance contexts, including an Anthropic-powered compliance Q&A tool at American Express and a home-equity assessment experience for seniors. Stands out for combining strong product instincts, typed full-stack implementation, and rigorous LLM evaluation/monitoring practices to improve trust, adoption, and operational efficiency.”

“Built an agentic medical coding system at Optum that combined LangGraph, LangChain RAG, Azure OpenAI, pgvector, and TypeScript to automate routine clinical coding while escalating risky cases to humans. The system automated about 40% of routine cases at roughly 92% accuracy, with strong production evals and observability using MLflow, Ragas, and DeepEval.”

“Backend/platform engineer from Dune Security with strong experience turning messy, fragmented workflows into reusable production systems. They’ve built a shared database abstraction layer, integrated multiple enterprise security platforms into a unified workflow, and shipped AWS Bedrock-powered security insight features with guardrails and human review.”

“Backend/AI engineer who has shipped an LLM-powered enterprise support-ticket agent at Comcast, building a production-grade microservices pipeline (FastAPI, SQS, Redis) with strong observability (OpenTelemetry/Splunk/Prometheus/Grafana) and reliability patterns (async, caching, circuit breakers, idempotency). Demonstrated quantified impact at scale—processing 10k+ tickets/day while improving response SLAs and routing accuracy through evaluation and human feedback loops.”

“Built and shipped an internal Financial Insights Assistant for banking analysts, owning the experience from workflow design through React frontend, FastAPI backend, and AI search integration. Particularly strong in making AI products usable and trustworthy by surfacing sources, experts, suggested prompts, and search history to improve confidence and speed.”

Mahima Mannava

Screened

Junior Software Engineer specializing in AI, LLM systems, and full-stack development

San Jose, CA3y exp

“AI/full-stack engineer who built a computer-usage agent end to end, including a split local/cloud architecture that used a vision LLM to drive real Chrome workflows while avoiding bot detection. Stands out for combining product-minded systems design, rigorous evals, and prompt iteration to achieve sub-2-second latency and a 20% reduction in automation failures in an early-stage environment.”

“Data/analytics-focused engineer who builds end-to-end KPI reporting and validation products used daily by plant leads and leadership to track yield, downtime, and defects. Combines Python/SQL + Power BI data pipelines with strong data-quality practices (automated validation, monitoring/alerts) and has experience designing scalable frontend architecture in TypeScript/React and working in distributed/microservices-style data systems.”

“Backend engineer who built an NL-to-SQL system at Target, using a multi-step LLM pipeline with vector-store schema retrieval and SQL validation to safely answer business questions. Strong in production FastAPI systems (async, Pydantic, Docker/Uvicorn, load balancing) and security (OAuth2/JWT, scopes, and database row-level security), with experience migrating Flask apps to FastAPI + PostgreSQL using strangler/feature-flagged canary rollouts.”

“Built a personal product, Pilly AI—an AI-powered e-commerce product Q&A widget embedded via a simple script tag and served via Cloudflare CDN—covering landing page, backend, database, and deployment end-to-end. Implemented OpenAI integration with prompt/context engineering, JWT-authenticated APIs, and Postgres (NeonDB), and successfully sold the product to a client while shipping in roughly two weeks.”

“AI/LLM engineer who built a production autonomous GenAI content ecosystem that generates short-form scripts, extracts viral highlights from long-form video, and dubs content into 33+ languages. Focused on making LLM outputs production-safe via schema enforcement, token-to-time alignment, critic-agent verification, and scalable async orchestration—cutting manual workflows by ~90% and saving $200k+ annually.”

“Backend/data engineer with production experience building secure Django/DRF APIs (JWT RS256 + rotating refresh tokens), background processing with Celery, and strong reliability practices (timeouts, retries/backoff, structured logging, audit trails). Has delivered AWS solutions spanning Lambda + ECS with IaC/CI-CD and built Glue/PySpark ETL pipelines with schema evolution and data-quality quarantine patterns; also modernized a legacy SAS pipeline to Python/PySpark with parallel-run parity validation and phased rollout.”

“Built and productionized a multi-agent, LLM-powered document understanding system to replace manual review of long documents, using LangGraph orchestration plus RAG to reduce hallucinations. Implemented layered reliability controls (structured templates, checker agent, and human-in-the-loop feedback) and reported ~40% speed improvement after orchestration; also has hands-on Airflow experience for scheduled data pipelines.”

“LLM/ML platform engineer with hands-on experience taking an LLM document summarization prototype into a production-grade service on AWS EKS, emphasizing low-latency inference, drift monitoring, and safe CI/CD rollouts (canary + rollback). Strong in real-time debugging of agentic/RAG systems (tracing, retrieval/index drift fixes) and in developer enablement through practical workshops (Docker/Kubernetes/FastAPI) plus pre-sales support via demos and benchmarks to close pilots.”

“ML practitioner with hands-on experience adapting diffusion models (DDPM + U-Net in PyTorch) to improve low-dose CT medical imaging quality via denoising and upsampling against high-dose ground truth. Also built a RAG workflow during a recent internship by cleaning client survey data, embedding with OpenAI text-embedding-3-large, and indexing in Pinecone with MD5 deduplication, alongside a strong emphasis on production-grade Python practices.”

“Product-focused full-stack engineer (70/30 app vs infra) with Accenture experience and recent AI workflow work, shipping end-to-end systems from React/TypeScript UIs through FastAPI backends to Postgres. Built an AI-driven data extraction platform with async job APIs, strict schema validation, and strong observability, and has operated AWS ECS-based deployments with real incident mitigation (DB connection exhaustion/latency under traffic spikes).”

“Embodied AI / robotics-focused ML engineer with experience at JPMorgan and EY building language-to-robot control systems that connect transformer/LLM intent to safe real-world robotic actions. Designed production-grade, low-latency architectures (Kafka/Redis, monitoring, CI/CD) and applied sim-to-real and model distillation to make research ideas deployable on physical systems.”

“LLM/GenAI engineer with US Bank experience building a production financial-document intelligence platform using LangChain/LangGraph, GPT-4, and Amazon OpenSearch. Delivered a RAG-based assistant for compliance/audit teams with grounded, cited answers, focusing on reducing hallucinations and latency, and deployed securely on AWS (SageMaker/EKS) with CI/CD and evaluation tooling (LangSmith, RAGAS).”

“At HPE, led and deployed an enterprise-grade LLM document intelligence platform for an insurance client, automating extraction from highly variable PDFs/scans/emails and raising field accuracy from 74% to 93%. Built a LangChain/Pinecone/OpenSearch RAG framework to cut hallucinations by 37% and operationalized LangSmith evals in CI, driving a 41% triage accuracy lift and >33% fewer incorrect resolutions while partnering closely with claims operations via HITL workflows.”

“Backend/AI workflow engineer with experience at AirKitchenz, Uber, and Vivma Software, building production systems on AWS (Lambda, DynamoDB, Step Functions). Has a track record of major performance wins (DynamoDB latency 2s to <150ms; Postgres query 2s to ~180ms) and shipping LLM-powered onboarding and ticket-routing workflows with strong guardrails (schema validation, confidence thresholds, human-in-the-loop escalation).”

“Built and shipped LLM/RAG systems in finance and startup settings, including a Goldman Sachs document intelligence platform that indexed ~8TB of regulatory filings and delivered cited, conversational answers with <2s latency—cutting compliance research by ~4.5 hours per batch. Also developed LangChain-based agent workflows at Finta to automate CRM enrichment and investor lookup with strong testing, tracing (LangSmith), privacy guardrails, and auditability.”