Senior Full Stack Engineer (AI / LLM)

Company: Ushakkaal Communications Ltd

Experience: 4–5 years

About Ushakkaal Communications Ltd

Ushakkaal Communications Ltd builds technology products that bring the power of modern AI to real-world users. We combine strong product engineering with deep expertise in large language models and AI infrastructure to deliver fast, reliable, and intelligent digital experiences at scale. Our team works at the intersection of full stack development and applied AI, turning cutting-edge research into products people actually use.

About the Role

We’re looking for a Senior Full Stack Engineer who is comfortable working across the entire stack, from responsive React front ends to scalable APIs and databases, and who brings strong working knowledge of LLMs and inference engineering. You’ll own features end-to-end, from the user interface down to how AI models are served, optimized, and integrated into production.

This is a senior, hands-on role. You’ll work closely with product, design, and AI/ML teams, mentor other engineers, and have real influence over architecture and technical decisions.

What You’ll Do
• Build and maintain web applications using React.js on the front end and Python/Node.js on the back end.
• Design, develop, and document clean, scalable, and secure RESTful APIs.
• Work with relational and non-relational databases (MongoDB, PostgreSQL, MySQL) and choose the right tool for each use case.
• Integrate LLMs into products, including prompt design, RAG pipelines, tool/function calling, streaming responses, and agentic workflows.
• Collaborate on LLM inference: model serving, latency and throughput optimization, batching, caching, and cost-efficient deployment.
• Deploy, monitor, and manage applications and AI services on AWS (EC2, S3, Lambda, RDS, or similar).
• Write testable, well-structured code, lead code reviews, and mentor junior engineers.
• Troubleshoot production issues, optimize performance, and improve system reliability across both application and AI layers.

What We’re Looking For

Must-Have
• 4–5 years of professional experience in MERN stack / full stack development.
• Strong proficiency in React.js: component architecture, hooks, state management, and modern tooling.
• Solid back-end skills with Node.js and experience building and consuming REST APIs.
• Working knowledge of MongoDB and at least one of PostgreSQL or MySQL.
• Hands-on experience with AWS in a development or deployment context.
• Strong understanding of LLMs: how they work, their limitations, prompt engineering, context windows, tokens, and embeddings.
• Practical experience integrating LLM APIs (OpenAI, Anthropic, open-source models, etc.) into production or substantial personal projects.
• Working knowledge of inference engineering concepts such as model serving, latency vs. throughput trade-offs, batching, streaming, KV caching, and quantization.

Nice-to-Have
• Experience with inference frameworks such as vLLM, TGI, TensorRT-LLM, Ollama, or llama.cpp.
• Experience with RAG systems and vector databases (Pinecone, Weaviate, pgvector, FAISS, etc.).
• Exposure to GPU-based deployments, model fine-tuning, or LLM evaluation and observability tools.
• Experience with TypeScript, Next.js, or server-side rendering.
• Familiarity with CI/CD pipelines, Docker, Kubernetes, or infrastructure-as-code tools.
• Understanding of authentication patterns (JWT, OAuth) and application security basics.
• Open-source contributions or a visible portfolio of AI-powered side projects.