This role is hands- on, technically deep, and suited for engineers who enjoy solving complex problems across systems, data, and AI.
WHAT YOU&039;LL BE DOING
INNOMIZE is seeking a Senior Full- Stack Developer with LLM/AI experience to help design, build, and scale our cloud- native AI platform. You will work across backend services, AI pipelines, and modern frontend interfaces, collaborating closely with product and engineering teams to deliver high- quality solutions.
Integrate and operate LLM- powered features using OpenAI and Anthropic Claude APIs.
Implement streaming and real- time features using SSE and WebSockets.
Evaluate and select models for different use cases (accuracy, speed, cost).
Work with PostgreSQL, including performance tuning and vector- based search.
Participate in system design, architecture decisions, and technical reviews.
Mentor junior engineers and contribute to a strong engineering culture.
Develop high- quality React applications, including real- time and AI- assisted user experiences.
Design and build LLM- powered APIs using Python (FastAPI) and JavaScript/TypeScript (NestJS).
Optimize prompts, token usage, latency, and cost across multiple LLM providers.
Write clean, testable, and maintainable code following solid principles.
Deploy and operate services on AWS (Lambda, ECS, S3, API Gateway).
YOUR SKILLS AND EXPERIENCE:
Bachelor&039;s degree in Computer Science or equivalent practical experience.
Comfortable with Docker, CI/CD, and production debugging.
Awareness of multi- model and multi- provider LLM strategies
Strong PostgreSQL knowledge (query optimization, indexing, vector extensions).
5+ years of professional software engineering experience.
Comfortable working with both backend (JavaScript / Python) and frontend (Angular / React preferred) technologies.
Practical experience working with LLM APIs (OpenAI, Anthropic, or similar).
Good at English communication.
Senior- level ownership and accountability.
Working knowledge of AWS or other cloud platforms.
Understanding of embeddings, vector search, and RAG architectures.
