Vetted Python Professionals

Manasa Pantra

Screened ReferencesStrong rec.

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

Stony Brook, NY2y exp

“Product-focused full-stack engineer at startup (Zippy) who shipped a production multi-agent AI system for restaurant operations plus payments workflows. Built end-to-end: RAG grounded on a Notion knowledge base, structured function-calling task routing, FastAPI/JWT multi-tenant backend, and a polished React+TypeScript owner dashboard. Has real production incident experience (duplicate Stripe webhooks) and reports ~94% task-routing accuracy under load.”

“Interned at Larsen & Toubro where they built and deployed an agentic RAG document question-answering system to reduce time spent searching documents and improve trustworthiness. Implemented ReAct-style multi-step orchestration with LangChain/LlamaIndex plus evidence-bounded generation, grounding/citations, and rigorous evaluation—cutting latency ~40%, hallucinations ~35%, and unsafe outputs ~40% while collaborating closely with non-technical business/ops stakeholders.”

“Co-founder and employee #1 who built Reva, a vertically integrated conversational CRM for multifamily leasing and resident services, leading product, engineering, and design from inception through acquisition. Combines deep enterprise product leadership with early AI experience, including a pre-LLM chatbot that drove a 400% lift in lead conversion and prior edtech work where AI-enabled learning tools improved struggling students by a full letter grade on average.”

“Backend engineer with experience building and modernizing high-volume healthcare transaction systems, including migrating Java services to Spring Boot microservices and adopting Kafka-based event-driven architectures. Strong focus on production reliability and operability (observability, CI/CD, standardized patterns) plus security (OAuth/JWT, RBAC, Postgres/Supabase RLS) and resilient stream processing (idempotency, DLQs).”

“Robotics software engineer (PhD background) who owned an end-to-end autonomy stack for a 2025 GTC demo, integrating ROS2/MoveIt2 with a high-fidelity NVIDIA Isaac Sim environment for regression testing and sim-to-real validation. Has hands-on experience optimizing MoveIt2 planning (parallel pipelines + evaluation metrics) and building outdoor Nav2 localization using dual EKF with GNSS and LiDAR/IMU sensor fusion; currently building simulation environments at Richtech Robotics.”

“Robotics software engineer/researcher focused on perception, SLAM, and sensor fusion, with hands-on experience taking systems from simulation to embedded/real-time deployment. Led transparent-surface (glass) detection using GDNet and achieved a major real-time speedup (~7–9 FPS to ~30 FPS) while preserving >90% recall, and has built ROS-based EKF GPS-IMU fusion plus profiled/optimized Visual SLAM for performance and memory stability. Also brings production-style deployment skills via Docker/Kubernetes orchestration of ML inference services with autoscaling and model update rollouts.”

“Frontend engineer at Mailchimp who leads end-to-end React/TypeScript features on the in-app homepage, including onboarding and campaign discovery components. Demonstrated measurable performance impact by cutting homepage LCP by ~2.5s and successfully shipped a major feature on an accelerated deadline using structured QA and staged rollout.”

“Built and productionized a tool-first, multi-agent framework that augments an anomaly detection model with domain context to generate trustworthy, evidence-backed anomaly explanations (including false-positive likelihood). Architected the platform to be model/orchestration/vectorDB agnostic (e.g., GPT + CrewAI + ChromaDB vs Claude + LangGraph + other vector DB) with strong performance, reliability, and OpenTelemetry-based observability. Also built a personal LangGraph-based "mock interviewer" agent that asynchronously fuses voice + live code input using state reducers, stop conditions, and fallback routing.”

“Software engineer with strong full-stack and platform experience (TypeScript/React/Node.js) who has built real-time analytics dashboards and microservices using RabbitMQ. Demonstrates production-minded decision-making under launch pressure (manual fallback for payment-impacting third-party API issues) and has delivered internal DevOps tooling that automates compliance checks via GitHub/Jira integrations.”

“Master’s student and Deep Learning teaching assistant who teaches LLM/VLM fine-tuning (including LoRA) and built a Hugging Face LLM fine-tuned for unit conversion, improving reliability by analyzing synthetic data and filling missing number-system conversion examples. Also implemented the Raft consensus protocol using gRPC in a distributed systems course with correctness validated by unit tests.”

“ML/AI practitioner in healthcare (Syneos Health) who has deployed production clinical NLP and risk models. Built a BERT-based physician-note information extraction system on Docker + AWS SageMaker (reported ~42% retrieval improvement) and automated retraining/deployment with Airflow and drift detection, while partnering closely with clinicians to drive adoption (reported ~18% readmission reduction).”

“AI/ML infrastructure-focused engineer who has built production RAG systems from scratch (Supabase/pgvector + OpenAI embeddings) and iterated using formal eval metrics to improve retrieval quality. Also debugged real-time audio issues in a LiveKit-based pipeline by correlating packet loss with VAD behavior, and has deep experience building brittle, customer-specific financial platform integrations in Python/Playwright (2FA, redirects, token refresh, rate limits).”

“Built and deployed a GPT-4-powered medical assistant for clinical staff to reduce time spent searching guidelines and EHR information, with a strong emphasis on safety and compliance. Uses strict RAG, confidence thresholds, and fallback behaviors to prevent hallucinations, and runs production-grade workflows orchestrated with LangChain/LangGraph plus Docker/Kubernetes/MLflow and monitoring for reliability and cost.”

“LLM/ML engineer who has shipped an enterprise RAG-based Q&A system (LangChain/LlamaIndex, FAISS + Azure Cognitive Search, GPT-3.5/4 via OpenAI/Azure OpenAI) to production on Docker + Kubernetes/OpenShift, tackling hallucinations, retrieval quality, latency/cost, and RBAC/IAM security. Also partnered with operations leaders to turn manual reporting into an LLM-powered summarization and forecasting dashboard driven by real KPIs and iterative stakeholder feedback.”

“Cloud-native integration engineer (Oracle/OCI) with strong production deployment and incident-response experience, including API gateway rollouts, observability (Prometheus/Grafana), and multi-layer debugging for payments systems. Built Python/FastAPI microservices and automation for customer-specific reporting and data sync, and has delivered major performance gains (45 min to <10) plus reliability improvements (MTTD reduced 40%+) through monitoring, playbooks, and resilient integration patterns (streaming/queuing, retries, secure tokens, VPC peering).”

“LLM/agentic workflow specialist with healthcare deployment experience who has taken LLM-based automation from prototype to production using operator-in-the-loop validation, RAG-style retrieval, RBAC, and monitoring for sensitive data compliance. Demonstrated real-time incident resolution (retrieval timeouts due to network/proxy misconfig) and strong GTM support—hands-on developer workshops and sales demos translating technical safeguards and real-time ETL into measurable ROI (70% ops reduction, ~$200K/year savings).”

“LLM/agentic systems practitioner focused on taking customer prototypes to production by hardening reliability (APIs, monitoring, security) and adding guardrails, evals, and incremental rollouts. Experienced diagnosing RAG/agent failures via structured tracing and fixing retrieval-quality issues (freshness checks, filters, schema enforcement). Also supports pre-sales by leading developer demos/workshops and building targeted POCs to address scalability/reliability objections and drive adoption.”

“Backend engineer with Walmart experience owning Python data-processing/integration services alongside ASP.NET Core. Has deployed containerized services to Kubernetes via OpenShift with Jenkins CI/CD and GitOps-style config management, and has led phased migrations modernizing VB6/classic ASP apps to ASP.NET Core on OpenShift/Azure. Also implemented Kafka-based real-time pipelines with a focus on reliability, idempotency, and observability.”

“Built a production real-time anomaly detection platform for high-frequency trading at HSBC, using a streaming stack (Pulsar + Spark Structured Streaming + AWS Lambda) and a transformer-based model combining time-series and numerical signals. Experienced in MLOps and safe deployment (Kubernetes, canary releases, MLflow/Grafana monitoring) and in aligning model performance with risk/compliance expectations through SLA-driven tuning and stakeholder-friendly dashboards.”

“Backend engineer at Cerebrone.ai building cloud-native Flask microservices for an AI-driven automation platform on GCP (Cloud Run/App Engine), including dedicated inference services integrating OpenAI and internal ML pipelines. Demonstrated strong performance and scalability wins across Postgres/SQLAlchemy optimization, multi-tenant (healthcare/HIPAA-grade) data isolation, and high-throughput background processing with Celery/Redis/RabbitMQ, with multiple quantified latency/CPU/throughput improvements.”

“Robotics-focused engineer from a senior capstone who built the backend motion-control software for a semi-autonomous line-following vehicle split across two ESP32s. Experienced in ROS 2 (DDS, lifecycle nodes, QoS) and in bridging microcontroller telemetry to a laptop ROS 2 stack over UART with custom structured protocols, using Gazebo simulation to tune PID and validate behavior before deploying to hardware.”

“Built a production RAG-based “unified assistant” that consolidates siloed company documents into a single chatbot while enforcing fine-grained access control via RBAC/metadata filtering with OAuth2/JWT. Experienced orchestrating LLM workflows with LangChain/LangGraph + FastAPI (async + caching) and measuring performance via retrieval accuracy and response-time SLAs. Also delivered a churn analytics solution with dashboards and automated retention campaigns using n8n.”

“Co-founded a healthcare AI startup building and deploying software directly with end users, emphasizing rapid shipping, deep user interviews, and workflow-first adoption. Has hands-on production deployment experience on AWS (including diagnosing a silent AWS App Runner failure caused by an ARM vs amd64 Docker build mismatch) and is motivated by customer-facing, travel-heavy roles to keep engineering tightly connected to real-world usage.”

“Built and deployed a production LLM system that scraped Google Maps menu photos, extracted structured prices via OpenAI, and cross-validated them against website-scraped data to automate data-quality verification at scale (replacing costly manual contractor checks). Demonstrates strong reliability instincts—precision-first prompting, output gating with image-quality metadata, and fuzzy matching/RAG techniques—plus solid orchestration (Dagster/Airflow) and observability (Sentry, Prometheus/Grafana).”