About ModalXModalX is an AI content-generation platform spanning video, audio, presentation, image, and chat generation, with a voice-based AI calling agent and an SMB onboarding product line. The platform integrates multiple LLM providers (Anthropic Claude, OpenAI, Google Gemini, xAI Grok, Perplexity) and media-generation services (HeyGen, D-ID, Synthesia, Gamma, VEO2, Stability, Ideogram, Canva, LiveKit). We serve both a public product (modalx.ai) and a white-labelled mobile PWA for Vodafone-Idea.
About the RoleWe are looking for a senior full-stack engineer who can own features end-to-end across our Go backend, React frontend, and Python AI workers. You will ship production features in a small, fast-moving team, work directly with the founders, and have significant influence on architecture and product direction. This is an individual-contributor role with room to grow into technical leadership.
What You'll Work On- Backend services (Go): HTTP APIs on the goji router, GORM over MySQL, WebSocket streaming for chat, Stripe payments, Firebase Auth integration, and AWS (S3, SES, CloudFront, Transcribe).
- AI orchestration: LLM routing across multiple providers, streaming responses, prompt engineering, tool-use pipelines, and Python AI workers shelled out from Go for chat, voice, PPT, image, and document generation.
- Frontend (React 18 SPA): Workspace chat UI, SMB onboarding wizard, calling-agent consoles, digital-twin avatar surfaces, payment flows, and mobile-responsive experiences.
- Voice & real-time: Calling-agent features using LiveKit, HeyGen LiveAvatar, AWS Transcribe, and WebSocket streaming.
- Platform work: Schema migrations, auto-generated DAO layers, Swagger API docs, observability (Sentry, LogRocket, Mixpanel, GA4), and CI/CD on GitLab.
RequirementsMust have- 7+ years of professional software engineering experience shipping production systems.
- Strong proficiency in Go — concurrency, HTTP services, context propagation, testing. Familiarity with GORM or a similar ORM.
- Strong proficiency in modern React (hooks, context, React Router v6), JavaScript (ES2020+), and at least one component library (MUI / Bootstrap).
- Working knowledge of Python 3 — enough to maintain, debug, and extend AI/ML scripts in production.
- Solid SQL / MySQL — schema design, query optimization, migrations.
- Production experience with LLM-based features — prompt engineering, streaming responses, tool/function calling, agents, or RAG pipelines. Familiarity with at least one of: Anthropic Claude API, OpenAI API, Google Gemini, or equivalent.
- Hands-on AWS experience — S3, IAM, SES, CloudFront, and/or similar services.
- Experience designing and consuming REST APIs and WebSocket streaming.
- Firebase Authentication (or comparable identity provider) integration experience.
- Strong fundamentals: data structures, system design, code review, debugging production incidents.
- Experience working in a dual-repo or microservices codebase and coordinating changes across services.
- Comfort in a Git-based workflow (GitLab or GitHub), CI/CD pipelines, and code review culture.
- Excellent written English and the ability to operate async with minimal supervision.
Strong plus- Payments integration with Stripe (subscriptions, webhooks, refunds).
- Experience with media generation or manipulation — video, audio, PPT, or image pipelines (HeyGen, D-ID, Synthesia, Gamma, ffmpeg, pptxgenjs, etc.).
- Experience with real-time voice / telephony — LiveKit, WebRTC, or similar.
- Experience with observability stacks — Sentry, LogRocket, Mixpanel, GA4.
- Prior work on multi-tenant SaaS or white-labelled products.
- Open-source contributions or side projects in AI / developer tools.
- Experience mentoring engineers and driving engineering hygiene (tests, docs, reviews).
Nice to have- Familiarity with goji, gorilla/websocket, swaggo, or smallnest/gen.
- Exposure to SQS / queue-based worker architectures.
- Experience with PWAs and mobile-optimized web.
Technical Environment You'll Be Working In- Backend: Go (goji, GORM, gorilla/websocket), MySQL, Firebase Admin, Stripe, AWS SDK, Swagger/swaggo, auto-generated DAOs via smallnest/gen.
- AI workers: Python 3 scripts for chat assistants (Claude, OpenAI, Grok, OpenRouter), voice assistant, PPT/image/audio/PDF/DOCX generation, image captioning and editing.
- Frontend: React 18 (CRA), React Router v6, MUI 5, Bootstrap 5, Firebase Auth, Stripe, Axios, LiveKit client, HeyGen LiveAvatar SDK, pptxgenjs, react-markdown.
- Infra: AWS (S3, SES, CloudFront, Transcribe), GitLab CI/CD, MySQL.
- Observability: Sentry, LogRocket, Mixpanel, Google Analytics 4.
What You Can Expect- End-to-end ownership of features that ship to real users and paying customers.
- Direct collaboration with founders and product leadership.
- A small team where your code and decisions have outsized impact.
- Exposure to the full breadth of the modern AI stack — multiple LLM providers, agents, voice, media generation.
- 100% remote, async-first working culture with at least 4 hours of daily overlap with IST.
How to ApplyPlease share:
- Your updated résumé / CV.
- GitHub / GitLab profile or links to representative work (production code, side projects, or OSS contributions).
- A short note (3–5 sentences) on one AI/LLM feature you have shipped in production — what it did, what you owned, and what you would do differently now.
