Senior AI Engineer with 11 years of experience building production backend systems and AI products. Focused on LLM workflows, structured outputs, RAG/model integration, evaluation, and reliability under ambiguous requirements, with strong debugging across application logic, data, model behavior, and user-facing workflows. Experienced delivering both commercial and self-hosted model deployments, improving latency and cost via routing, caching, batching, and inference optimization. Known for failure-resistant API design, traceability, and test/evaluation loops that prevent regressions before release.…

TAKESHI YAMAMOTO

Senior AI Engineer with 11 years of experience building production backend systems and AI products. Focused on LLM workflows, structured outputs, RAG/model integration, evaluation, and reliability under ambiguous requirements, with strong debugging across application logic, data, model behavior, and user-facing workflows. Experienced delivering both commercial and self-hosted model deployments, improving latency and cost via routing, caching, batching, and inference optimization. Known for failure-resistant API design, traceability, and test/evaluation loops that prevent regressions before release.…

Available to hire

Senior AI Engineer with 11 years of experience building production backend systems and AI products. Focused on LLM workflows, structured outputs, RAG/model integration, evaluation, and reliability under ambiguous requirements, with strong debugging across application logic, data, model behavior, and user-facing workflows.

Experienced delivering both commercial and self-hosted model deployments, improving latency and cost via routing, caching, batching, and inference optimization. Known for failure-resistant API design, traceability, and test/evaluation loops that prevent regressions before release.

See more

Skills

Experience Level

Python
Expert
Large Language Model
Expert
Prompt Engineering
Expert
API
Expert
SQL
Expert
Docker
Expert
PostgreSQL
Expert
TypeScript
Expert
Redis
Expert
Kubernetes
Expert
Java
Expert
AI Chatbot
Expert
GPT
Expert
Claude
Expert
GitHub CoPilot
Expert
Cursor Composer
Expert
AI Data Labelling
Expert
Jira
Intermediate
Django
Intermediate
Backendless
Intermediate
See more

Language

Javanese
Fluent
English
Advanced
Estonian
Beginner

Work Experience

Senior AI Engineer at BPW Consulting
May 1, 2025 - July 1, 2026
Turned ambiguous product concepts into production LLM features using Python and FastAPI: defined API boundaries, structured outputs, validation rules, and fallback paths, then rolled out via user-facing workflows. Built evaluation loops using curated examples, schema checks, semantic quality scoring, and regression cases to catch prompt/model/parsing regressions before release. Debugged AI feature failures spanning malformed inputs, retrieval context, model responses, backend state, and UI-visible behavior; added traceable intermediate outputs and failure classifications to speed diagnosis. Improved a latency-sensitive LLM workflow by introducing response caching, concurrent retrieval, timeout budgets, and model routing, reducing median test latency by ~35% while preserving evaluation quality. Used Claude Code, Cursor, and GitHub Copilot daily to implement, generate tests, refactor, and debug, verifying changes against application behavior and production constraints.
AI Platform Engineer at Breakwater Technology
November 1, 2023 - April 1, 2025
Integrated commercial and open-source LLMs behind provider-neutral Python adapters while keeping application contracts stable to enable model changes based on quality, latency, cost, and operational needs. Implemented self-hosted inference with vLLM and containerized model serving, configuring batching, memory limits, health checks, and request queues. Designed extraction workflows that converted unstructured text into typed JSON using schema-constrained generation, deterministic validation, repair attempts, and human review routing. Added bounded retries, circuit breaking, timeouts, and fallback models around external inference dependencies so partial provider failures degraded individual requests rather than blocking entire workflows. Built Pytest-based integration suites covering invalid payloads, unavailable models, malformed structured responses, and database failures. Profiled token usage and queue delay to identify cost/latency bottlenecks and adjusted model selection and batchi
Machine Learning Engineer at Sensor Fields
May 1, 2018 - October 1, 2023
Built Python inference services separating feature preparation, model execution, and API delivery so model versions could change without coupling application releases to training workflows. Developed asynchronous data pipelines with PostgreSQL and message queues, validating schemas and isolating malformed records before downstream prediction/automation. Containerized inference workloads with Docker and Kubernetes, defining resource limits, readiness checks, and safer rolling deployments. Reduced median benchmark latency by ~30% via profiling serialization, database access, and inference execution, then adding batching and Redis-backed caching. Created regression tests around feature transformations, model-version transitions, invalid input, and dependency failures. Instrumented services with OpenTelemetry metrics and traces for request latency, error classes, queue depth, and resource saturation to improve production diagnostics. Reviewed designs, guided engineers on service decomposit
Backend Engineer at Rail Baltic Estonia
July 1, 2016 - April 30, 2018
Developed Python and Java REST backend services with PostgreSQL persistence, enforcing validation at application and database boundaries. Implemented background workers for long-running jobs with idempotent task handling and bounded retries to recover safely from transient dependency failures. Built automated data checks for missing identifiers, conflicting states, and schema violations before records entered downstream processing. Diagnosed slow database operations using execution plans and application traces, then adjusted indexes/query patterns for more predictable response times. Expanded integration tests around API contracts and database migrations to catch incompatible changes early. Supported Docker-based deployments and investigated dev vs shared-environment configuration differences using logs and reproducible test cases. Participated in design reviews focused on service boundaries, failure behavior, data ownership, and maintainability.
Backend Engineer at Rail Baltic
July 1, 2016 - April 1, 2018
Developed Python/Java backend services with REST interfaces and PostgreSQL persistence, enforcing validation at application and database boundaries. Implemented background workers for long-running jobs with idempotent task handling and bounded retries for transient dependency failures. Built automated data checks for missing identifiers, conflicting states, and schema violations before downstream processing. Diagnosed slow database operations using execution plans and application traces, then revised indexes and query patterns for more predictable response times. Expanded integration tests around API contracts and database migrations to catch incompatible changes pre-deployment. Supported Docker-based deployments and investigated configuration differences between development and shared environments using logs and reproducible test cases. Participated in design reviews covering service boundaries, failure behavior, data ownership, and maintainability.
Software Engineer at Adcash
June 1, 2015 - June 1, 2016
Implemented backend features in Java and SQL, extending service endpoints while preserving established API contracts and persistence behavior. Investigated defects using logs, database inspection, and reproducible test cases, correcting edge conditions involving malformed requests and missing data. Added unit and integration tests for service changes covering normal requests, invalid parameters, and database updates before release. Optimized selected SQL queries by reviewing execution behavior to remove redundant reads and improve consistency for frequently accessed endpoints. Supported deployments and post-release checks by reviewing health/logs and key workflows, escalating unexpected behavior with diagnostic evidence. Documented recurring debugging procedures and known failure modes to help teammates reproduce and apply consistent fixes across environments.

Education

Bachelor of Science in Computer Science at University of Tartu
August 1, 2010 - May 1, 2015
Bachelor of Science in Computer Science at University of Tartu
August 1, 2010 - May 1, 2015
Bachelor of Science in Computer Science at University of Tartu
August 1, 2010 - May 1, 2015

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Computers & Electronics, Professional Services
    AI Clinical Documentation Assistant

    • Built an LLM documentation workflow that transformed caregiver notes and voice transcripts into structured care records, summaries, and follow-up tasks using Python, FastAPI, and schema-constrained generation.
    • Implemented Pydantic and JSON Schema validation with automatic repair and validation-driven human-review routing for incomplete, contradictory, or malformed model outputs.
    • Developed RAG over care-plan context plus an evaluation suite covering unsupported claims, missing fields, invalid dates, and contradictory outputs; instrumented retrieval, inference, validation, and latency with OpenTelemetry.
    • Added provider-neutral support for commercial and open-source models with Redis-backed context caching, allowing model changes without coupling the application workflow to one inference provider.