Satvik Adyanthaya
AI Engineer
Management: Under a year
SQL
TypeScript
Python
C++
C#
C
API Design: 6/10
Scalability & Performance: 6/10
System Architecture: 6/10
Active 3 days ago
Invite to interview
Download CVCV
Overview
Technical skills
Timeline
Roles
Overview
Full-stack Python developer (middle level) focused on building backend APIs and AI-assisted services with an emphasis on async, modular services. Strongest proven skill is integrating AI/model and async services into production APIs, shown concretely by backend/app/services/ai_service.py which implements Bedrock invoke, embedding generation and response handling. Public code shows limited evidence of hardened test infrastructure, contract testing, load benchmarks or CI-based mutation/flake engineering, so large-scale SRE and rigorous QA practices are not evidenced.
Technical skills
Languages
6
SQL
TypeScript
Python
C++
C#
C
Python
10
FastAPI
SQLAlchemy
Pydantic
Celery
Boto3
Asyncio
Alembic
HTTPX
Aiohttp
structlog
Frontend
4
React.js
Next.js
Tailwind CSS
React Query
AI/ML
3
PubMed
AWS Bedrock
Instructor
Other
16
Power BI
AWS
Neo4j
PostgreSQL
GitHub
.NET
AG Grid
BERT
Uvicorn
Rest API
Git
Tableau
AI Agents
Machine Learning
Knowledge Graph
Multi-Agent Systems
Timeline
AI Product Workshop Instructor
•
Head+
Ain Center for Entrepreneurship and Innovation
•
Full-Time
Led a hands-on AI product workshop for 15+ students, employees, and faculty. Created step-by-step training focused on translating product requirements into implementation, including Git workflows, cloud architecture, deployment, and troubleshooting. Supported participants with practical exercises to build deployable workflows and resolve integration issues.
Git
AI Researcher
•
Middle
Ain Center for Entrepreneurship and Innovation
•
Full-Time
Built and shipped an 11-module biomedical research platform using Python and PubMed-BERT, leveraging Neo4j-based knowledge storage with hybrid retrieval and source validation. Incorporated researcher feedback into workflow and system changes, documenting failure modes and using structured root-cause analysis to improve reliability. Integrated an AI/ML advisory workflow for founders by defining requirements, success metrics, technical risks, and implementation priorities.
Python
PubMed
Neo4j
Technical Product Lead
•
Lead
Tenure
•
Full-Time
Translated stakeholder interviews into process maps, functional requirements, acceptance criteria, and role-based workflows for an AWS pilot involving ~30 organizations. Planned and ran end-to-end workflow validation across multiple integrations, documenting results, investigating exceptions, and driving issues to resolution. Produced SOPs, onboarding materials, KPI dashboards, and stakeholder briefs to support implementation, UAT-style validation, and ongoing operations.
AWS
Amity University
Bachelor's Degree •
Biotechnology; Business Management
Research Project Lead
•
Lead
Organic Recycling Systems
•
Full-Time
Analyzed operating, capacity, cost, and process data across two waste-to-energy initiatives to identify bottlenecks and improvement opportunities. Led operations research teams and created executive briefs that connected quantitative findings with technical tradeoffs, implementation priorities, and investment decisions. Contributed to measurable gains in conversion efficiency by refining process recommendations.
Research Intern
•
Junior
Glenmark Pharmaceuticals
•
Internship
Applied statistical analysis and experimental design across multiple pharmaceutical product programs to support evidence reviews and product decisions. Validated findings across several laboratory functions and reconciled test evidence with underlying assumptions. Produced concise research briefs for cross-functional stage-gate reviews across U.S. and LATAM market contexts.
Product Engineer
•
Middle
Adyanthaya Ventures
•
Full-Time
Built a full-stack commerce platform using relational product data and an AI chatbot to connect customer, product, inventory, pricing, and order workflows in a single application. Used SQL and Power BI to validate pricing and inventory data across large SKU sets, investigating exceptions and tracking key metrics. Leveraged findings to support operational decisions during a period of month-over-month user growth.
SQL
Power BI
Middle Backend Developer
Confidence: Medium API Engineer
A backend-focused engineer (senior level) building production AI-enabled web services and orchestration systems. Proven skill: designing and implementing async, agent-based orchestration and ingestion pipelines with concrete artifacts like app/agents/discovery_orchestrator.py and the ingestion scheduler. Not evidenced: explicit large-scale distributed system ownership across multiple services, a long migration history for schemas, or formal SRE-level runbooks and capacity testing in public code.
API Design
6/10
How well APIs are designed
API design is pragmatic and consistent (versioned v1 endpoints, typed request/response models) but shows limited evidence of advanced API resiliency patterns such as idempotency key handling, per-endpoint timeouts or explicit API version migration strategy.
Data Layer & Database
5/10
Working with databases
Data layer uses modern async SQLAlchemy, AsyncPG and pgvector and has a migration tool declared (Alembic), but there is little public evidence of a long migration history, hand-tuned SQL, or explicit transaction/isolation-level decision documentation.
Scalability & Performance
6/10
Handling load and speed
Clear attention to scalability: async execution, scheduler, token-pooling and Redis-backed state, plus parallel processing in orchestration; evidence of rate-limiting and background workers. Caching/invalidation strategy and formal load-test artifacts are not visible.
System Architecture
6/10
Overall system structure
Deliberate modular boundaries and orchestrator patterns (agent layer, ingestors, orchestrator, typed IR) indicate considered architecture decisions; the repo also contains program-level execution guidance. Some decomposition choices (microservice vs monolith tradeoffs, cross-service contracts) are present but not exhaustively documented as runtime SLAs or degradation plans.
Evidence
satvikOS/humanovo/backend/app/agents/base.py
satvikOS/humanovo/backend/app/agents/controller.py
satvikOS/11_ARCHDISC_CONVERGENCE_EXECUTION_PROGRAM.md
Security & Auth
5/10
Protecting data and access
Authentication and token handling, input validation via Pydantic, and guardrails for PHI/PII are present; good use of established libraries for JWT and password hashing. Evidence of advanced token lifecycle (refresh/revocation), formal dependency audit, or systematic secret management is limited in the analyzed files.
Reliability & Observability
6/10
Stability and monitoring
Reliability is carefully considered: checkpointing, transactional state updates, scheduler health, structured logging and observability touchpoints are present. Mature operational patterns (circuit breakers, advanced backoff policies, documented SLO/alerting) are not fully visible in the public files.
Expertise
Backend AI & LLM• Middle
Databases & Vector Storage• Middle
Messaging & Real-time• Middle
Microservices & API Architecture• Middle
Python• Middle
System Architecture• Middle
Technologies
C#
Rest API
.NET
FastAPI
Celery
Aiohttp
structlog
Recommendations
- Lead API and LLM orchestration work: implement production RAG pipelines, provider fallbacks, quota-aware request routing, and cost instrumentation using the existing discovery_orchestrator and MultiModelLLM patterns.
- Build robust data-platform features: schema evolution and migration history, transactional integration tests and hand-tuned queries for the SQLAlchemy layer (app/core/database.py and Alembic pipelines).
- Develop scalable ingestion and real-time services: harden the scheduler, add formal rate-limits, backpressure and retry-with-jitter policies, and extend Redis-backed state with metrics/alerts.
- Own backend reliability and CI/CD: expand the existing mutation/gate approach into documented SLOs, automated chaos checks and release-time artifact validation.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories:
Middle QA Engineer
Confidence: Medium Generalist
Full-stack Python developer (middle level) focused on building backend APIs and AI-assisted services with an emphasis on async, modular services. Strongest proven skill is integrating AI/model and async services into production APIs, shown concretely by backend/app/services/ai_service.py which implements Bedrock invoke, embedding generation and response handling. Public code shows limited evidence of hardened test infrastructure, contract testing, load benchmarks or CI-based mutation/flake engineering, so large-scale SRE and rigorous QA practices are not evidenced.
Test Automation Frameworks
1/10
Building automated tests
Test Automation Frameworks - minimal evidence of a shared automation framework, fixtures, factories or deliberate flake engineering; repo has testable application entry points but no visible, project-wide test harness or parallelization config.
Test Coverage & Strategy
1/10
What and how to test
Test Coverage & Strategy - little evidence of risk-based test stratification, boundary/property tests or mutation-based coverage; pydantic request models exist which enable stronger validation but comprehensive negative/boundary tests are not visible.
API & Integration Testing
2/10
Testing how parts work together
API & Integration Testing - clear API surface and modular services that enable integration tests, but no contract testing (Pact/Schemathesis) or schematized contract assertions are present in the analyzed files.
Performance & Load Testing
1/10
Testing speed under load
Performance & Load Testing - no formal load or SLO-driven performance harness seen; async design and a realtime streaming service suggest performance awareness but not structured load testing artifacts.
Bug Reporting & Analysis
1/10
Finding and describing bugs
Bug Reporting & Analysis - minimal public artifacts demonstrating closed-loop bug reports, reproducible minimal repros, or RFC-style root-cause analysis; usual engineering comments and README notes exist but no visible external issue/PR cross-linking in these files.
CI Test Integration
1/10
Running tests automatically
CI Test Integration - basic package.json scripts and a readable project layout that make CI wiring straightforward, but no CI workflow files or evidence of matrixed test runs, artifact collection or quarantine mechanics are present in the analyzed files.
Expertise
Unit & Component Testing• Junior
Industries
Financial Services• Middle
Software• Middle
Technologies
SQLAlchemy
Asyncio
Pydantic
HTTPX
Uvicorn
Boto3
Alembic
Recommendations
- Develop backend API features and AI integration (embeddings, RAG, model orchestration) using the existing FastAPI / async pattern demonstrated in backend/app/services.
- Implement and own integration and contract tests for the API surface (contract testing, schema validations and negative-path cases using pydantic models as a basis).
- Build reproducible CI pipelines with artifact collection and mutation/negative controls to protect critical flows (FFP checks, transfer simulations, embedding generation).
- Design end-to-end tests for financial compliance features and RAG pipelines, including property-based inputs and explicit failure-mode assertions.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories:
Junior Frontend Developer
Confidence: Medium UI Engineer
Frontend UI engineer (Middle) specializing in pragmatic Next.js and React application work with attention to useful utilities and production scaffolding. The strongest proven skill is building tidy app scaffolding and small, dependable abstractions for API and app runtime concerns, evidenced by OS-DIP/frontend/lib/api-client.ts and the Next.js project manifests (ArchDisc-Landing package.json, next.config.ts). The public code shows careful, pragmatic engineering but lacks evidence of sizable system design, deep performance benchmarking, extensive automated tests, or hardened accessibility work.
UI Component Architecture
3/10
How interface parts are built
Small but deliberate component and hook design for Next.js apps; pragmatic separation of concerns but no evidence of a custom design-system rollout or deep component architecture choices across many apps.
Evidence
ArchDisc-Landing/package.json: Next.js + Tailwind dependency and app scaffold
OS-DIP/frontend/lib/api-client.ts: small, well-scoped API client wrapper
ArchDisc-Landing/src/app/robots.ts: app-level runtime metadata indicating app structure
Responsive & Cross-browser
3/10
Works on all screens and browsers
Uses Next.js and Tailwind with conventional responsive strategies; shows basic sitemap/robots and config readiness but no advanced container queries, RTL or explicit cross-browser feature-detection artifacts.
Evidence
ArchDisc-Landing/next.config.ts: Next.js config present
OS-DIP/frontend/next.config.ts: project-level Next configuration
Performance Optimization
2/10
Speed of the interface
Minor performance attention in utilities and app-level scaffolding, but no measured perf artifacts, bundle analysis, or large-list virtualization in the human-authored files reviewed.
Evidence
OS-DIP/frontend/lib/api-client.ts: single centralized request wrapper (small perf hygiene)
ArchDisc-Landing/package.json: build scripts and dependency choices that enable modern bundlers
Accessibility & Semantics
2/10
Usable for everyone
Some signals of SEO/robots and sitemap care, but no concrete accessibility engineering (focus management, ARIA, CI a11y checks) in the human-authored sources inspected.
Evidence
ArchDisc-Landing/src/app/sitemap.ts: explicit sitemap generation
ArchDisc-Landing/src/app/robots.ts: robots metadata setup
State Management & Data Flow
2/10
Managing data in the app
Simple, correct API client and dependency declarations suggest awareness of server-state flows, but no demonstrated advanced state machines, request-cancellation or optimistic update patterns in the human-authored code.
Evidence
OS-DIP/frontend/package.json: @tanstack/react-query present in dependencies (app-level server-state tool)
OS-DIP/frontend/lib/api-client.ts: centralized fetch wrapper for server calls
UX & Visual Polish
3/10
Look and feel quality
Visual polish and UX attention visible in project scaffolding and a small number of UI assets; however most polished CSS and canvas utilities in the provided set were in AI-labeled files and therefore were not credited as human-authored evidence.
Evidence
OS-DIP/frontend/app/ticker-animation.css: a dedicated animation for a UI ticker
ArchDisc-Landing/package.json: Next.js + Tailwind choices enabling modern UI polish
Industries
Financial Services• Middle
Sports• Junior
Technologies
TypeScript• since 2025 • Junior
Tailwind CSS
Next.js
React.js
React Query
AG Grid
Recommendations
- Develop customer-facing Next.js interfaces and internal admin UIs where clear data flows and a simple design system are required.
- Build a small component library and documented token system to consolidate UI patterns and accelerate cross-project consistency.
- Lead implementation of app-level state and server-state flows (React Query) and add measurable performance and accessibility audits (Lighthouse, axe) into CI.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories: