Innovantes is building AI-enabled digital solutions for enterprise clients across automotive, healthcare, and analytics-driven domains. We are looking for a Backend Engineer with strong experience integrating and architecting AI services (LLMs, vision, speech, embeddings) into scalable production systems.
This role focuses on using AI services effectively , not building ML models from scratch.
- Design and build scalable backend architectures using Node.js
- Develop secure, production-grade APIs that integrate AI services such as:
- LLMs (text generation, summarization, classification)
- Vision APIs (image analysis, OCR)
- Speech APIs (STT/TTS)
- Architect AI workflows , including:
- Prompt orchestration
- Tool/function calling
- Streaming responses
- Multi-step reasoning pipelines
- Build provider-agnostic abstractions (avoid lock-in to one AI vendor)
- Handle cost control, rate limits, retries, fallbacks, and caching
- Ensure data security and privacy , especially for enterprise clients
- Collaborate with frontend, analytics, and product teams
- Strong expertise in Node.js (Express / NestJS preferred)
- API-first design (REST; GraphQL optional)
- Async processing, queues, background jobs
- Cloud-native architecture experience (GCP/AWS/Azure)
- Hands-on experience integrating:
- Text generation
- Embeddings + semantic search
- Classification & extraction
- Deep understanding of:
- Token limits, context windows
- Prompt design vs system design
- Latency vs accuracy trade-offs
- Structured outputs (JSON schemas, tools/functions)
- SQL (MySQL/Postgres)
- Familiarity with vector databases (conceptual + practical)
- Caching strategies (Redis or equivalent)
- Python for AI tooling, agents, or batch workflows
- Experience with RAG systems
- Experience building AI-powered enterprise tools (CRM, analytics, dashboards)
- Exposure to compliance-conscious environments (PII, data governance)
