Vetted Celery Professionals

“AI/LLM engineer who has shipped production RAG chatbots using LangChain/OpenAI with FAISS and FastAPI, focusing on real-world constraints like context windows, concurrency, and latency (reported ~40% latency reduction and <2s average response). Experienced orchestrating AI pipelines with Celery and fault-tolerant long-running workflows with Temporal, and has applied NLP model tradeoff testing (Word2Vec vs BERT) to drive measurable accuracy gains.”

“DevOps engineer (State Farm) with hands-on ownership of Python backend services and data pipelines, deploying microservices and workers on Kubernetes using GitOps (Argo CD). Has led complex cloud-to-on-prem/hybrid migrations with staged cutovers and rollback planning, and built Kafka-based real-time streaming pipelines with schema governance, autoscaling, and strong observability.”

“Backend Python engineer who has built an LLM agentic tutoring/assignment helper with a custom pipeline for parsing visually complex textbooks (integrating AlibabaResearch VGT and implementing missing preprocessing from the paper), improving RAG grounding with ~90% cleaner extracted text. Also led major platform scaling work by refactoring monolithic image processing into Celery-based async microservices on AWS (GPU/CUDA + S3), and implemented Kafka streaming for payment webhooks with strict ordering, idempotency, and multi-zone fault tolerance.”

“IBM Power/AIX engineer who has owned a 150+ LPAR AIX 7.x estate with VIOS/HMC/vHMC and PowerHA in production, including real outage and failover recoveries. Also brings modern DevOps/IaC experience—built Jenkins pipelines deploying to AKS and implemented Terraform on AWS with remote state, locking, and drift management.”

“Backend engineer with Accenture and EY experience building multi-tenant financial/compliance platforms in Python/Flask. Strong in performance and scalability work across SQLAlchemy/PostgreSQL (EXPLAIN ANALYZE, indexing, N+1 fixes) and in reliability improvements using Celery + Redis. Has integrated external AI model APIs for document extraction/invoice validation with robust background processing, retries, and output cleaning.”

“At Trellis, built and shipped a production multi-agent, authenticated GenAI chatbot for sensitive financial account inquiries (loan/payment lookups), using dynamic model routing to control latency and cost while improving accuracy. Implemented prompt-injection defenses (Meta Prompt Guard), RAG with LangChain, and LLM-as-a-judge evaluation; the system cut manual support call volume by 40%+ and was refined through close collaboration with QA-driven user testing.”

“Built and productionized a RAG-based semantic search system for video-derived data, focusing on measurable success metrics (p95 latency, reliability, cost/request) and strong observability (prompt versions, retrieved docs, tool calls, token usage). Experienced in diagnosing real-time issues in LLM/agentic workflows and in supporting go-to-market efforts through tailored technical demos, rapid POCs, and post-close onboarding.”

“India-based engineering leader/player-coach managing ~20 people and three products, while still shipping hands-on in Python/Golang across 8–10 microservices deployed on GCP (Kubernetes) and AWS (ECS). Has led end-to-end delivery (design through QA) and owned production reliability improvements (including building a Slack alerting bot). Strong domain exposure in utilities (MDM/meter readings, billing/rate calculations) and financial integrations (GL code tagging), plus side projects in Golang around LLM API cost-optimization.”