{ "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json", "basics": { "name": "Dmitriy Stepanov", "label": "Principal Engineer — big data · backend · AI engineering", "email": "stepanov.dg@gmail.com", "url": "https://cv.stepanovs.dev/", "summary": "14 years building data platforms — from Hadoop-era product engineering to petabyte-scale cloud migrations. Currently migrating a Fortune-50 ingestion platform to Spark-on-Kubernetes, Flink, and Iceberg, and building agentic AI tooling that automates the engineering workflow around it.", "location": { "city": "San Diego", "region": "CA" }, "profiles": [ { "network": "LinkedIn", "username": "dmitriy-stepanov", "url": "https://www.linkedin.com/in/dmitriy-stepanov/" }, { "network": "GitHub", "username": "stepanovdg", "url": "https://github.com/stepanovdg" }, { "network": "Telegram", "username": "streamsmith", "url": "https://t.me/streamsmith" } ] }, "work": [ { "name": "EPAM Systems", "position": "Principal Data Engineer (since 2025-07; phase 1 EPAM team lead of 4; now IC outstaffed into client ingestion team)", "startDate": "2025-01", "summary": "Client: Fortune-50 consumer-electronics company (under NDA)", "highlights": [ "Led the pipeline-migration workstream of a multi-PB Hadoop/HDFS → AWS S3 platform migration: dependency-phased migration of ~220 Spark pipelines (ingestion, compaction/latest, hybrids) to Spark-on-Kubernetes in ~6 months — evaluated dependency lineage and migrated leaf-first so each phase gated on the previous one's verified success. AWS-funded program.", "Personally migrated 20–30 of the pipelines, including converting legacy custom Hadoop MapReduce jobs (Wikipedia-corpus data prep for LLM training) to Spark, alongside newer JSON-flattening pipelines.", "Designed the data-parity sign-off process for the migration: HDFS and S3 ran overlapping; both copies landed on a common platform where Spark-notebook comparison jobs proved result equivalence before each dataset was signed off and cut over.", "Dual role — EPAM team lead (4 engineers), co-ran the migration process with the delivery manager while contributing as a hands-on engineer. Framework-conformant jobs migrated fast; final months were the complex custom tail (e.g. Wikipedia LLM-training data-prep jobs).", "Ingestion-team engineer for the client's core pipeline: Cassandra → Kafka (table archiver + direct-event producers) → Kafka → S3 incremental → per-dataset compaction/latest jobs. Owns schema updates and job changes across the fleet; platform includes an in-house dataset-registry system + schema/config/metrics services.", "Drove a self-service epic for data analysts: a realtime-data enrichment wizard that generates schema-update tickets as structured JSON — machine-readable so schema changes can be AI-automated end-to-end (agent flow → PR creation). Built the companion AI chat assistant (web) on the Anthropic API with streaming, tool calling, and guardrails.", "Migrating the Kafka-export layer from Spark to Flink: replacing ~1-hour long-running pseudo-streaming Spark jobs (Kafka → S3 JSON, secondary job JSON → deduped Parquet, external watchdog scheduler restarts) with Flink-native pipelines. In progress.", "Participated in the table-format/catalog evaluation (AWS Glue vs Nessie vs in-house service); Iceberg-on-S3 selected, migration underway.", "AI-assisted engineering suite around Claude Code, used daily for a near-fully-automated workflow (task gathering → prioritization → ticket flow): an IaC tool, then a Terraform provider, managing Claude Code instances from config with profile support (self-adjusting in realtime); an \"AI artifactory\" pipeline that watches team + OSS AI repos, curates changes through security/poisoning review and performance evals, and installs the vetted results; a router skill choosing best model×effort config per repeatable task; a local RAG system replacing memory files (vector search, no size limits); a ticket workflow with team creation, communication, and retrospectives.", "Stepped in as the single point of contact for the customer during a delivery-manager gap (Aug–Sep), keeping the ingestion workstream aligned and delivering while the team was without a DM; integrated into the client-side team quickly and picked up the ingestion domain.", "Onboarded and mentored engineers joining the ingestion team — the go-to person for ramping new joiners on the domain and codebase.", "As AI champion on the programme, drove and evidenced the account's engineering AI-maturity to Level 2.1 (RAG Green, above the target of 2): authored the L2 evidence artefact and the Level-3 readiness roadmap — an agentic multi-agent Spark-to-AWS migration factory scoped over the ~1,000-job backlog.", "Built the team's AI-usage metrics tooling (per-day spend, DAU/WAU, limit-hit detection) and instrumented the team — daily-active AI usage measured at 87.9%, past the Level-2 >70% bar — and designed its released-only build->review->scan->publish CI/CD pipeline, closing a laptop supply-chain security risk.", "Grew a reusable AI factory — a 108-skill shared library, 39 committed AI-context files, and 4 team plugins published to a released-only internal marketplace — and delivered an AI-SDLC enablement session demonstrating these capabilities to the team." ] }, { "name": "EPAM Systems", "position": "Team Lead (~10 people) — vAuto Oracle→AWS migration & optimization program", "startDate": "2023-11", "endDate": "2024-09", "summary": "Client: COX Automotive", "highlights": [ "Architected and delivered an extensible Python framework for Oracle → S3 (Parquet) migration of a multi-PB estate — client kept expanding scope, so the framework shipped with extension points well beyond the original spec; owned architecture decisions, project structure, DevOps (GitHub Actions, Terraform, CI/CD, linters) and task delegation for the ~10-person team." ] }, { "name": "EPAM Systems", "position": "Key Engineer / Infrastructure Engineer / Performance Analyst", "startDate": "2020-06", "endDate": "2023-10", "summary": "Client: Verizon (Thingspace IoT)", "highlights": [ "Eliminated a chronic distributed-locking failure mode in the IoT device-scheduling system: the Zookeeper-lock-based scheduler hard-locked routinely (lock limits + timing races), failing over-the-air device updates. Redesigned it to an append-only, event-sourced model in the warehouse — locking removed entirely, OTA-update failures from this cause eliminated.", "Overhauled team CI/CD: introduced Artifactory, cut build times, automated security scans into the pipeline; served as the team's DevOps point of contact and release manager (tagging, scans, docs, deploy coordination).", "On-prem → AWS migration of the Thingspace IoT platform; refactored the legacy self-written gateway to KrakenD (config, K8s components, middleware plugins); added Micrometer/Prometheus metrics across all team services; externalized shared libraries (metrics, logging, security, config)." ] }, { "name": "EPAM Systems", "position": "Team Lead / Key Engineer", "startDate": "2019-11", "endDate": "2020-05", "summary": "Client: Verizon (NetSense IoT / Big Data)", "highlights": [ "Team-led the big-data stream on Verizon's Smart Cities / NetSense IoT platform (Team Lead / Key Engineer) — Spark/Scala pipelines processing large-scale connected-device data.", "Built a change-data-capture pipeline (Aurora binlog -> Debezium -> Kafka -> Spark on EMR), unified the team's Spark CI/CD, and drove a fleet-wide EMR upgrade." ] }, { "name": "EPAM Systems", "position": "Onsite Team Lead / coordinator (1 onsite + 6 offshore big-data engineers)", "startDate": "2018-08", "endDate": "2019-11", "summary": "Client: Sephora USA", "highlights": [ "Onsite team lead coordinating a 7-person big-data team (1 onsite + 6 offshore) on Sephora's commerce data platform.", "Led the team's delivery of a real-time sales-analysis system plus batch and streaming ETL on Spark / Spark Streaming (Scala) over Azure ADLS + Data Factory, with Avro schema-registry-governed data." ] }, { "name": "EPAM Systems", "position": "Key Engineer", "startDate": "2018-02", "endDate": "2018-08", "summary": "Client: Honeywell", "highlights": [ "Built ingestion and enrichment pipelines on Apache Spark / Spark SQL over Azure Data Lake for a smart-home telemetry platform serving a fleet of ~3 million connected thermostats, producing utilization reporting.", "Added Spark Structured Streaming with a real-time Random-Forest enrichment model; migrated the platform from Spark Standalone to Spark-on-Kubernetes and hardened Kafka/Zookeeper (Elassandra = Cassandra + Elasticsearch)." ] }, { "name": "EPAM Systems", "position": "Big Data platform product engineer", "startDate": "2013-09", "endDate": "2018-08", "summary": "Client: Pentaho / Hitachi Vantara (product engineering)", "highlights": [ "Big-data platform product engineer on the Pentaho Data Integration & Business Analytics suite (Java/OSGi) for ~5 years — authored the Hadoop-vendor shims (NamedClusterVFS), the EMR shim, a Kerberos security layer, Azure-HDInsight-over-Knox support, and the Spark execution-engine integration.", "Supported 4 major releases and 25+ service packs; built a custom test-automation framework that reduced manual regression testing to zero, including globalization coverage across EN/FR/DE/JA." ] }, { "name": "EPAM Systems", "position": "Engineer — BI/data integration (ODI, Informatica, WebLogic)", "startDate": "2012-05", "endDate": "2013-09", "summary": "Client: Oracle", "highlights": [ "Early-career engineer on Oracle BI / data-integration solutions (Oracle Data Integrator, Informatica, WebLogic) — pipeline development plus debugging, monitoring, and incident troubleshooting of BI systems." ] } ], "education": [ { "institution": "Belarusian State University", "area": "Radiophysics and Computer Technologies (Intelligent Systems dept.)", "studyType": "Specialist, physicist-engineer" } ], "certificates": [ { "name": "OpenAI: Cyber Deployment Practitioner", "date": "2026-08" }, { "name": "Anthropic: Claude Certified Architect – Professional", "date": "2026-07-17" }, { "name": "Google Cloud: Certified Partner Specialist Gemini Enterprise Agent Development", "date": "2026-07-15" }, { "name": "Google Cloud: Certified Partner Specialist Gemini Enterprise Deployment", "date": "2026-07-13" }, { "name": "Anthropic: Claude Certified Architect – Foundations", "date": "2026-03-19" }, { "name": "Anthropic: Claude Certified Architect – Foundations Early Adopter", "date": "2026-03" } ], "skills": [ { "name": "Programming Languages", "keywords": [ "Java", "Python", "Go", "Scala (Spark)", "SQL" ] }, { "name": "Big Data", "keywords": [ "Apache Spark (batch + streaming, on K8s/EMR)", "Apache Kafka (+ Connect, Schema Registry, Debezium CDC)", "Apache Flink", "Apache Iceberg", "Hadoop ecosystem (HDFS, MapReduce, Hive, HBase, YARN)", "Cassandra", "Airflow" ] }, { "name": "Cloud & Infrastructure", "keywords": [ "AWS (S3, EMR, Lambda, ECS, Step Functions, EventBridge, Aurora)", "Kubernetes (+ Spark-on-K8s, Helm)", "Terraform/OpenTofu (+ Terragrunt; wrote a custom provider)", "Azure (ADLS, Data Factory, HDInsight)", "Docker" ] }, { "name": "AI Engineering", "keywords": [ "Anthropic API (streaming, tool calling, guardrails)", "Agentic systems (Claude Code, MCP, skills, multi-agent orchestration)", "RAG / vector search", "Forward-deployed engineering", "LLM evaluation harnesses" ] }, { "name": "Observability & DevOps", "keywords": [ "CI/CD (Jenkins, GitHub Actions, GitLab CI, Artifactory)", "Prometheus / Grafana / Micrometer", "Splunk", "Performance engineering (JMeter, profiling)" ] }, { "name": "Spoken Languages", "keywords": [ "English", "Russian" ] } ], "projects": [ { "name": "Personal platform engineering", "highlights": [ "Personal end-to-end agentic delivery system: ideas → roadmap → backlog → sprints → tasks, with parallel agent teams working unsupervised inside sprints (ledger-backed planning, 3-reviewer merge gates, retrospectives). Runs the personal data platform (Iceberg/Nessie/Kafka/sqlmesh on K8s) and homelab IaC estate." ] } ], "meta": { "canonical": "https://cv.stepanovs.dev/resume.json", "version": "v1.0.0", "lastModified": "2026-10" } }