Full Stack Developer – AI Systems

Job Title: Full Stack Developer – AI Systems
Experience: 2–3 years
Location: Hybrid/Gurgaon
Employment Type: Full-time
About the Role
We're looking for a full stack Software Engineer who can build end-to-end product features — from backend services to user-facing interfaces — and also integrate AI/LLM capabilities into production systems. This role spans frontend and backend engineering, with applied AI work layered on top (RAG, LLM integration, agents) rather than model research or training.
Responsibilities
Full Stack Engineering (core focus)
Design, build, and maintain scalable backend services and APIs using Python and FastAPI
Build responsive, performant frontend interfaces using React (or similar frameworks) that consume these APIs
Architect microservices-based systems with clean separation of concerns and scalability in mind
Build real-time APIs and WebSocket-based communication for streaming/interactive use cases, and wire them into live frontend experiences
Implement asynchronous processing (async/await, task queues, message brokers) for high-throughput workloads
Design backend data flow, caching strategies, and system architecture for performance and reliability
Own features end-to-end — from API design and data modeling to UI implementation and deployment
Deploy and manage services on AWS/GCP, using Docker and Kubernetes
Set up and maintain CI/CD pipelines and basic MLOps practices for shipping AI features reliably
Write clean, tested, well-documented, production-grade code across the stack; participate in code reviews
AI/ML Integration (applied focus)
Integrate LLMs into product features via APIs (OpenAI, Anthropic, open-source models, etc.), surfaced through intuitive UI/UX
Use LangChain (or similar frameworks) to orchestrate LLM workflows and agents
Design and manage vector databases for embeddings storage and semantic search
Build evaluation frameworks to monitor AI feature accuracy, latency, and cost
Improve inference latency and cost-efficiency of deployed AI features
Collaborate with product and design teams to translate business requirements into AI-powered features, front to back
Stay current with LLM, RAG, and agent tooling advancements
Required Qualifications
Bachelor's degree in Computer Science, Engineering, AI/ML, or related field
2–3 years of professional software engineering experience
Strong programming skills in Python and JavaScript/TypeScript
Hands-on experience with FastAPI (or similar backend frameworks) and React (or similar frontend frameworks)
Practical experience integrating LLMs into applications (not necessarily training them)
Experience with RAG pipelines and LangChain or comparable orchestration tools
Familiarity with vector databases and embedding-based search
Solid understanding of microservices architecture and full stack system design
Experience with cloud platforms (AWS and/or GCP), Docker, and Kubernetes
Understanding of asynchronous programming and event-driven systems
Comfort with HTML/CSS and building responsive, accessible UI
Strong analytical and problem-solving skills
Preferred Qualifications
Experience with agentic workflows, tool-calling, or multi-step LLM pipelines
Exposure to model serving/inference optimization (ONNX, Triton, quantization basics)
Familiarity with voice AI / ASR / speech technologies (nice-to-have, not core)
Experience with SQL/NoSQL databases (PostgreSQL, MongoDB, Redis)
Experience with state management libraries (Redux, Zustand, etc.) and modern build tooling
Contributions to open-source projects or AI-related side projects

Work arrangement
No