Senior AI Developer (Full-Stack)

We are seeking a Senior AI Developer (Full-Stack) to build and validate AI-powered semantic matching features for a test intelligence platform used across multiple product lines. You will own end-to-end delivery from vector indexing and evaluation methodology to API and UI presentation.
Responsibilities
Design the semantic match evaluation corpus with label definitions, sampling methodology, and adjudication rules
Build and maintain a semantic vector index including gateway client integration, incremental embedding, HNSW indexing, and neighbor-query services
Implement embedding backfill runs with throughput controls and spend governance across multiple datasets
Implement semantic matching selection logic with off-until-measured gating and confidence-based routing
Build a pipeline that converts high-confidence semantic matches into durable deterministic links
Implement a direct delta observation route that derives change magnitude and area signals from content-level deltas
Build an area-to-test translation bridge using LLM-assisted classification with batched calls, structured outputs, versioned proposal sets, and budget limits
Develop enrichment agents that classify and tag records and write results back to a unified data store
Create a frontend presentation layer with ranked lists, score explanations, details views, override workflows, and export flows
Implement calibration and settings surfaces that help QA teams interpret scores and thresholds
Add degraded-run detection, channel health surfacing, and safety-net broadening rules to improve reliability
Requirements
3+ years Python backend experience with FastAPI or equivalent
Vector database experience using PostgreSQL/pgvector, HNSW indexing, and similarity query design
LLM API integration experience with batched calls, structured outputs, spend caps, and retry handling
Embedding pipeline experience including text assembly, normalization, incremental embedding, and model/version stamping
Evaluation corpus experience for semantic similarity tasks including label definitions, sampling strategy, and precision measurement
Strong project ownership skills to deliver MVP features end-to-end across backend, ML workflows, and frontend surfaces
Advanced SQL skills including window functions and materialized views
Strong REST API skills with OpenAPI contract adherence
Strong React skills for data-heavy scoring, ranking, and calibration interfaces
Strong Specification Driven Development (SDD) practices for clear contracts and measurable outcomes
Strong communication skills to explain confidence, thresholds, and tradeoffs to non-ML stakeholders
Upper-Intermediate English (B2) proficiency
Nice to have
Experience with enterprise AI gateways or Gemini embedding models
Experience integrating QMetry, Zephyr, or QTM4J APIs
Knowledge of Snowflake export pipeline design (Snowpipe or bulk load)
Experience with LLM-based classification and reclassification pipelines
Gaming or AAA game QA domain knowledge
We offer
International projects with top brands
Work with global teams of highly skilled, diverse peers
Healthcare benefits
Employee financial programs
Paid time off and sick leave
Upskilling, reskilling and certification courses
Unlimited access to the LinkedIn Learning library and 22,000+ courses
Global career opportunities
Volunteer and community involvement opportunities
EPAM Employee Groups
Award-winning culture recognized by Glassdoor, Newsweek and LinkedIn
EPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.

Work arrangement
Yes