AI product and technology leader with 7+ years building conversational AI and LLM agents for healthcare, fintech, and telecom.
What I have shipped:
• MEDvidi (US telehealth): production AI agents for patient communication across SMS, voice, and web chat. 40% of SMS sessions resolved without staff. Patient response time cut from about 30 minutes to under 1 minute.
• MTS AI (telecom): led a 50-person cross-functional product team and the first commercial LLM rollout in MTS Group. Automation up 10% with user satisfaction maintained. 667+ model versions trained, 20+ custom models in production.
• Alfa-Bank (banking): predictive conversation flows raised automation by 20% in key assistant scenarios. AI-driven tooltips used in 5 to 10% of all sessions. Part of the team that took Alfa-Bank to #1 in chatbot development among Russian banks for the first time (Markswebb, 2022).
How I work:
• Agent architecture: LangGraph and LangChain pipelines, LLM tool calling, RAG, structured outputs, deterministic backend rules, prompt and model versioning.
• LLM evaluation: scenario simulations at scale, golden conversations, regression suites, tool-call correctness checks, pre-release model evaluation.
• Observability and release: tracing, feature flags, controlled rollout, latency and cost monitoring, incident-to-test loops.
• Regulated workflows: PHI-aware design, safe escalation, human-in-the-loop handoff, uncertainty handling.
I own the whole cycle: product strategy, agent architecture, evaluation, observability, and production results.
Looking for a Senior, Lead, or Head of AI Product role where agents go to production and quality is measured. Based in Valencia, Spain. Open to remote (EU, US) and relocation within Spain.
Experience: 7 years
Yearly salary: $110,000
Hourly rate: $55
Nationality: 🌏 Remote
Residency: 🇪🇸 Spain
Experience
Senior Product Manager, AI
MedVidi 2025 - 2026
Built and launched AI agents and automation infrastructure for a US telehealth company: patient communication, lead management, and internal operations: Built and launched production AI agents for patient communication across SMS, voice, and web chat, integrated with internal systems, patient workflows, lead management, and support operations. 40% of SMS sessions resolved by the agent without staff involvement. Reduced patient response time from about 30 minutes to under 1 minute by moving first-line communication to AI agents with safe escalation to staff. Designed production agent architecture and behavior: LangGraph and LangChain pipelines, LLM tool calling, structured outputs, API and tool contracts, deterministic backend rules, prompt and model versioning. Benchmarked dozens of model and prompt configurations. Built LLM evaluation practice for agents and tools: thousands of scenario-level simulations across hundreds of curated cases, golden conversations, regression checks, tool-call correctness validation, incident-to-test loops. Set up observability and release management: tracing, prompt/model/tool versioning, feature flags, controlled rollout, latency and cost monitoring, production issue analysis. Defined product and guardrail metrics: automation rate, goal completion, classification quality, escalation accuracy, reliability, cost, patient experience. Embedded healthcare constraints into product logic: PHI-aware design, safe escalation, human handoff, uncertainty handling, deterministic enforcement of business rules.
AI Product Lead, Conversational AI & Voice Automation
MTS AI 2023 - 2025
Led product and technology for large-scale text and voice assistants in telecom customer service: platform roadmap, automation growth, quality metrics, cross-functional delivery: Led the first commercial LLM integration for conversational AI in MTS Group: automation up 10% with user satisfaction maintained. Improved assistant comprehension by 7% in voice and 24% in text through ML features, classifier optimization, and structured evaluation. Built and led a 50-person cross-functional product team, moving from a resource-based model to a dedicated product structure with clear ownership, delivery routines, and KPI-based priorities. Defined and executed the roadmap for conversational automation: ML-based intent classification, sentiment analysis, satisfaction prediction, user segmentation, LLM adoption. Oversaw training of 667+ model versions and deployment of 20+ custom production models for intent classification, sentiment analysis, and satisfaction prediction. Built a data-driven improvement loop: human and AI annotation of 500,000+ user phrases, SQL-based analysis and BI reporting, production impact evaluation. Defined quality metrics and analytics across automation rate, Voice of Customer, GCR, FCR, classification quality, and A/B testing. Translated enterprise customer requirements into product scope, roadmap priorities, delivery plans, and investment estimates.
Technical Product Lead / Lead Product Analyst / Conversational AI Analyst
Alfa-Bank 2019 - 2023
Progressed across product analytics and platform leadership roles, working on banking assistant automation, NLU optimization, platform migration, release validation, personalization, and advanced assistant UI capabilities: Led the development and evolution of a conversational AI platform for banking assistants, focusing on automation, personalization, NLU quality, scalable assistant architecture, and stable release processes. Managed platform migration, ensuring backward compatibility, ML model support, scenario logic consistency, and release reliability across banking assistant scenarios. Designed personalization and integration logic for banking assistants, including user segmentation, adaptive automation levels, buttons, tooltips, widgets, and JSON-based integration requests. Created test datasets and evaluation processes to measure pre-release model quality using F1 score, accuracy, recall, and scenario-level performance metrics. Automated release validation through pre-release testing, error analysis, and release guidelines for assistant scenarios and ML models, improving deployment reliability and reducing production issues. Launched AI-driven tooltips across banking channels, used in 5-10% of all sessions and contributing to a 3-5% automation increase. Developed predictive conversation flows using user data, increasing automation by 20% in key scenarios; contributed to Alfa-Bank ranking #1 in chatbot development among Russian banks by Markswebb in 2022 (for the first time).
Skills
analyst
architecture
product-lead
product-manager
strategy
tech-lead