OSNOVA

# ai researcher in metalearning 

- client: ai product development company from germany
- product: cogit - ai agent-based automation platform
- experience: machine learning, self-optimization systems, prompt engineering, llm evaluation
- tasks:
   - architect the agent.maker meta-framework with sub-agents (instruction.maker, config.maker, screen.maker)
   - develop self-improvement loops for iterative prompt refinement
   - build evaluation framework for agent output quality (instructions.md, config.yaml generation)
   - implement llm observability and tracing (phoenix/arize integration)
   - create quality metrics for generated agents (tool usage accuracy, task completion rate)
   - develop prompt mutation strategies based on execution feedback
   - build fitness evaluation for config parameters (model selection, temperature tuning)
   - implement learning mechanisms from agent execution logs
   - create benchmarks comparing models (gemini vs claude) for different agent tasks
- languages: python
- libraries: google adk, anthropic sdk, phoenix tracing, pydantic, yaml

# senior full-stack developer

- company: ai product development company from germany
- product: cogit - ai agent-based automation platform
- experience: web development, python backend, typescript frontend, ai agent interfaces
- tasks:
   - build frontend and backend components for agent management dashboard
   - develop cogit.panel interface for agent interaction (react/typescript)
   - implement endpoints for agent communication and creation
   - build real-time status updates during agent workflows
   - implement session management and conversation history
   - create user authentication flow with jwt tokens
   - improve multi-tenant data isolation across frontend and backend
   - improve azure services (blob storage, ai search, email)
   - improve email processing interface with outlook/graph api
- languages: typescript, python 
- libraries: react, nestjs, redux toolkit, prisma, azure sdk, fastapi, google adk 

# senior business development executive

- company: ai product development company from germany  
- product: cogit - ai agent-based process automation platform
- experience: 5+ years in b2b sales, outreach campaigns, c-level engagement across global markets
- tasks:
   - develop and execute end-to-end outreach campaigns from icp creation to deal closure
   - build relationships with executives in target industries (manufacturing, services, govt) across business functions (order management, procurement, customer service, admin)
   - craft tailored outreach strategies with personalized messaging for ai/automation buyers
   - conduct pre-launch research and deliver compelling introductory calls
   - identify client pain points and align cogit solutions to business needs
   - nurture prospects through email and linkedin 
   - manage sales pipeline from lead generation to proposal delivery
   - collaborate with product team to translate market feedback into features
- markets: dach, emea, north america
- tools: linkedin sales navigator, hubspot, pipedrive, apollo, zoominfo, outreach.io
- focus: enterprise saas sales, ai/automation solutions, long-term client relationships
 

# senior product designer

- company: ai product development company from germany
- product: cogit - ai agent-based automation platform
- experience: 10+ years in product design and product management, b2b saas enterprise
- tasks:
   - conceptualize novel interaction patterns between humans and ai agents
   - design dynamic interfaces for ai-native workflows (panel, orb, voice)
   - sketch and prototype onboarding flows for complex ai products
   - develop conversational ux patterns for agent creation and management
   - define business models and pricing strategies for saas offering
   - create design system matching cogit brand aesthetic
   - design multi-agent status indicators and feedback patterns
   - plan responsive experience across desktop and mobile
- focus: human experience design, sketching, ai-native interfaces
- tools: figma, prototyping, user research, business modeling

# senior software architect

- client: ai product development company from germany
- product: cogit - ai agent-based automation platform
- experience: multi-tenant saas architecture, azure cloud, ai/ml systems
- tasks:
   - design scalable architecture for agent.maker meta-framework
   - architect multi-tenant data isolation (tenants, users, agents, data sources)
   - plan azure container apps deployment and ci/cd pipelines
   - design tool registry and agent registry for dynamic loading
   - establish security patterns (managed identity, key vault, secrets)
   - define cost optimization strategy for llm api usage (model selection, caching)
   - create observability architecture (tracing, structured logging, metrics)
   - architect fast inference integration for conversational agents
   - plan vector embeddings and search infrastructure
- languages: typescritp, python, sql, yaml
- technologies: azure, postgresql, docker, github actions