12.08.2026 aktualisiert

**** ******** ****
verifiziert
Premiumkunde
100 % verfügbar

AI Product Engineer | AI Agents • AWS • Node.js • TypeScript • Python • Go

Warsaw, Polen
Nur Remote
CKAD & AWS Solutions Architect Certified
Warsaw, Polen
Nur Remote
CKAD & AWS Solutions Architect Certified

Profilanlagen

CV-Mateusz-Kolodziejczyk.pdf

Über mich

AI Engineer, 8+ yrs full-stack experience. Production code in TypeScript, Python, Go. Builds AI agent systems, voice pipelines, RAG apps, and serverless architectures. Cut latency from 600ms to under 50ms, reduced cloud costs 40%+. Custom AI tooling: Claude Code, MCP servers, AI agents.

Skills

JavaScriptAPIsAgile MethodologieCloudfrontAmazon S3ArchitekturDistributionspolitikUnit TestingMicrosoft AzureCloud ComputingCloud-EngineeringCode CoverageDatenbankenDevOpsDistributed ComputingAmazon DynamoDBElasticsearchGitHubIdentitätsmanagementInfrastrukturPostgreSQLMicrosoft Message QueuingMongoDBMySQLNeo4jNode.jsMeldesystemeProduktlinienentwicklung (Software)ProduktionssystemeSoftware ArchitectureRabbitMQRedisAzure Machine LearningNext.jsAmazon Simple Notification Service (SNS)SQLStreamingSystem DesignTypeScriptAWS CDKPulumiTestenLifecycle ManagementIstioFlaskLiefer-PipelineExpress.jsPrompt EngineeringMontage und DemontageGenerative AIAWS LambdaInfrastructure as Code (IaC)AWS VPCBackendAWS ECSCloudformationFastAPIEvent Driven ArchitectureGit FlowKubernetesCloudflareApache KafkaGraphQLRoute53Funktionale ProgrammierungApi DesignCloudwatchApi-GatewayNestJSFintechRestful ApisAmazon Simple Queue ServicesTerraformgRPCArtificial Intelligence Markup Language (AIML)Aws IotServerless ComputingDockerProgramming LanguagesMicroservices
AI/ML Engineering: AI Agents, MCP, Voice AI, Conversational AI, AI Avatars, LLMs, VLMs, LangChain, LangGraph, RAG Systems, MLOps, MLFlow, Knowledge Graphs, AWS Bedrock, AWS AgentCore, Azure OpenAI, Pinecone, pgvector, ChromaDB, Neo4j, Embeddings, Reranking, Hybrid Search, Speech-to-Text
(STT), Text-to-Speech (TTS), OpenAI API, Anthropic Claude API

Real-Time Media & Voice: LiveKit, LiveKit Egress, WebRTC, WebSockets, Azure Speech Services, Azure TTS, Media Streaming, Real-Time Communication

AI-Assisted Development & Rapid Prototyping: Claude Code, OpenAI Codex, PI, Cursor, Docker Sandboxes

Fullstack Development: TypeScript, Next.js, Nest.js, React, Python (FastAPI, Flask, Django), Go, Node.js, Express.js, GraphQL, REST, gRPC, Microservices, Serverless

Cloud Architecture: AWS (EC2, ECS, EKS, Fargate, Lambda, Step Functions, API Gateway, Bedrock, AgentCore, SageMaker, S3, DynamoDB, RDS, Aurora, ElastiCache, CloudFormation, CDK, CloudFront, Route 53, VPC, SQS, SNS, EventBridge, Kinesis, CloudWatch, IAM, Cognito, KMS), Microsoft Azure

Infrastructure & DevOps: Terraform, CDK, Pulumi, Docker, Kubernetes, Helm, ArgoCD, GitOps, Istio, GitHub Actions, GitLab CI/CD, CircleCI, Localstack, Supabase, CKAD (Certified Kubernetes Application Developer)

Databases & Messaging: PostgreSQL, MySQL, MongoDB, DynamoDB, Redis, Elasticsearch, Neo4j, Apache Kafka, RabbitMQ, Amazon Kinesis, MQTT, Event-Driven Architectures

Security & Compliance: OAuth 2.0, OIDC, JWT, IAM, Cognito, RBAC, Multi-Tenant Security, Secrets Manager

Erfahrung

Berufserfahrung5 - 10 Jahre
Freelancer seit2019

Sprachen

EnglishverhandlungssicherPolishMuttersprache

Projekthistorie

Senior AI Engineer

Freelance Client

Internet und Informationstechnologie

>10.000 Mitarbeiter

Cut AI avatar-render cost and latency by serving precomputed clips on cache hits instead of re-rendering through the model every time. Designed and built a real-time caching layer for an AI avatar video platform on LiveKit. Architected a capture-and-replay system using LiveKit Egress: prewarming avatar responses in hidden rooms, persisting muxed audio/video artifacts, and replaying them through a dedicated publisher participant that bypasses the third-party managed avatar renderer entirely on a hit.

Senior Software Engineer — Backend & Platform Engineer

Gaming / Internet & IT Client

Internet und Informationstechnologie

50-250 Mitarbeiter

Engineered and maintained the Kubernetes platform for a large-scale gaming infrastructure using kOps on AWS, ensuring high availability, reliability, and safe cluster upgrades across multiple environments. Leveraged TypeScript, Pulumi, and GitOps workflows to automate provisioning, reconciliation, and lifecycle management of Kubernetes clusters and backend systems.

Led implementation of a custom Pulumi provider orchestrating kOps operations (cluster replace, reconcile, rolling updates, instance group pruning, kubeconfig generation, admin token management, and cluster validation), enabling fully automated and reproducible cluster operations across CI/CD pipelines. Managed critical stateful backend components (Redis, RabbitMQ, Elasticsearch, Cloudflare Tunnel). Implemented CI/CD pipelines for microservices and Kubernetes platform deployments.

Technologies: TypeScript, Pulumi, Kubernetes, kOps, AWS (EKS, IAM, VPC), Redis, RabbitMQ, Elasticsearch, Cloudflare Tunnel, GitOps, Docker, CI/CD

AI Engineer – Agent Orchestration & Data Integration

fullbeam.ai

Internet und Informationstechnologie

10-50 Mitarbeiter

Owned the AI orchestration layer: designed and implemented the multi-agent system coordinating LLM and VLM models for automated product analytics. Built the integration layer that fetched and normalised data from external systems into a format the agents could reason over, handling RRWEB session replay data at scale. Implemented the embedding and vectorisation pipeline, storing and indexing vectors with pgvector and using similarity search to surface relevant session context for each agent query. Responsible for agent routing logic, context assembly, and wiring MCP tool-calling so models could read and write structured output directly to downstream systems without human-in-the-loop steps.

Established an organisation-wide Claude Code setup, standardising AI-assisted development workflows across the engineering team and reducing time-to-production for new features significantly.

Technologies: LLMs, VLMs, AI Agents, MCP, LangGraph, LangChain, RAG, Pinecone, pgvector, Python, FastAPI, TypeScript, Next.js, React, AWS (Lambda, S3, DynamoDB), Docker, GitHub Actions, Claude Code

AI Engineer – Voice AI for Market Research

getConvo.ai

Internet und Informationstechnologie

50-250 Mitarbeiter

Built the MVP Go backend with a custom voice-to-voice pipeline, writing the core service that connected Azure Speech-to-Text, Azure OpenAI, and Azure TTS in sequence with low enough end-to-end latency for natural conversation. Built the agent layer on top to steer interview flow, handle topic transitions, and detect when to probe deeper vs. wrap up. Used WebSockets throughout to keep the browser client in sync without polling.

Technologies: Go, AI Agents, Azure OpenAI, Azure TTS, WebSockets, React, React Native, AWS (Lambda, Kinesis, DynamoDB, S3), Docker, Terraform

AI & Software Engineer – BLE Signal Processing & GenAI Integration

360 Health & Performance

Pharma und Medizintechnik

10-50 Mitarbeiter

Developed backend for iOS application fetching users' Respiratory Rate data from a third-party Bluetooth device and calculating wellness scores. Utilized AWS CDK for Infrastructure as Code and AWS Amplify for GraphQL schema creation. Built custom algorithm to reduce noise from respiratory rate readings. Partnered with domain experts and a Fortune 500 software company to ensure medical correctness of algorithms.


Senior Software Engineer — Backend & Platform Engineer

Major Music Distribution Client: Media & Entertainment

Medien und Verlage

>10.000 Mitarbeiter

Designed and owned backend for iOS application responsible for streaming audio. Reduced average streaming latency from ~600ms to under 50ms using Terraform, TypeScript, Docker, and Kubernetes with Istio service mesh. Led the design and deployment of a microservices architecture using Kubernetes, Istio, and PostgreSQL within AWS RDS, ensuring improved scalability and fault tolerance.

Designed and delivered 10+ production microservices forming a Kafka-driven data platform for royalty reporting and analytics, reducing end-to-end response time by ~80% through asynchronous processing and service decoupling. Reduced production bug escape rate by ~60% by enforcing contract testing, CI gating, and 90% unit test coverage (Jest). Provided guidance and coding reviews for junior developers.

Technologies: TypeScript, Node.js, Terraform, Docker, Kubernetes, Istio, PostgreSQL, AWS RDS, Apache Kafka, Jest, Microservices, CI/CD

Software Engineer — Backend & Platform Engineer

Major German Insurance Provider - Regulated Industry

Versicherungen

>10.000 Mitarbeiter

Developed backend for two applications: one managing computation of client employees' pension schemes, the other supporting client teams. Implemented Event-Driven Architecture using AWS SQS, AWS SNS, and AWS EventBridge, increasing system throughput and enabling real-time notifications and seamless third-party integrations. Utilized Cross-Account IAM Roles for secure inter-backend communication. Worked in tandem with a renowned AWS Partner company in Germany.

Technologies: TypeScript, AWS CDK, AWS SQS, AWS SNS, AWS EventBridge, Cross-Account IAM, Jest, Event-Driven Architecture, Serverless

Full-Stack Developer

Magictown Group
Developed and managed web-based solutions for apparel company focusing on interactive websites with React and JavaScript. Administered hosting and DNS resolutions using AWS and Cloudflare, improving website latency by 200%.

Zertifikate

CKAD: Certified Kubernetes Application Developer

The Linux Foundation

2024

AWS Certified Solutions Architect – Associate

Amazon Web Services

2021

AWS Cloud Practitioner

Amazon Web Services

2021

Portfolio

Kontaktanfrage

Einloggen & anfragen.

Das Kontaktformular ist nur für eingeloggte Nutzer verfügbar.

RegistrierenAnmelden