We are looking for a Senior Full-Stack Developer who is passionate about building scalable products and excited to work at the intersection of Generative AI, Large Language Models (LLMs), and Agentic AI systems. In this role, you will collaborate closely with LLM developers, Agentic AI engineers, and platform architects to build cutting-edge applications, internal tools, and enterprise products powered by SandLogic's Shakti LLMs, LingoForge, and advanced AI frameworks.
Full-Stack Engineering
The core responsibilities for the job include the following:
- Design, develop, and maintain scalable frontend and backend components for AI-powered applications.
- Build responsive, performant UI dashboards and web interfaces for model interaction, analytics, and monitoring.
- Develop backend services, APIs, microservices, and databases that interact with LLMs and agentic systems.
- Optimize application performance, reliability, and security across the full stack.
LLM And Agentic AI Collaboration
- Work hand-in-hand with LLM developers to integrate LLMs, Lexicons, and multimodal models into applications.
- Collaborate with Agentic AI (Agenti) engineers to build workflows involving autonomous agents, retrieval systems, and state machines.
- Implement RAG pipelines, prompt-orchestrators, and middleware connecting applications with LLM endpoints.
- Participate in fine-tuning, evaluation, and testing of LLM-powered features.
Product And Platform Development
- Contribute to design discussions for AI features, model interfaces, analytics layers, and customer-facing capabilities.
- Build reusable components, code libraries, and DevOps-ready modules for rapid development.
- Drive clean code practices, documentation, code reviews, and engineering standards.
Continuous Learning And Innovation
- Actively explore LLM fundamentals, inference optimization, embeddings, vector databases, and agentic frameworks (AutoGen, LangChain, Agenti).
- Stay updated with the latest advancements in Generative AI, web technologies, and engineering best practices.
- Identify opportunities to enhance system intelligence, automate workflows, and integrate new AI capabilities.
Core Full-Stack Skills
The core requirements for the job include the following:
- Strong expertise in JavaScript/TypeScript, Node.js, and modern backend frameworks (Express, NestJS, FastAPI).
- Proficiency in React, Node.js, or similar frameworks for frontend development.
- Experience building scalable REST APIs and WebSocket-based services.
- Hands-on experience with at least one cloud platform (AWS, GCP, Azure).
- Strong understanding of relational and NoSQL databases (PostgreSQL, MongoDB, Redis).
AI And LLM-Related Skills (Preferred / Willingness To Learn)
- Familiarity with LLM APIs, inference endpoints, embeddings, RAG pipelines, or vector databases (FAISS, Pinecone, Milvus).
- Exposure to LangChain, AutoGen, Agenti, or agentic workflow orchestration.
- Understanding of model interactionsprompting, fine-tuning basics, and latency optimization (preferred, not mandatory).
- Ability to work with AI engineers to design and integrate AI-based features.
General Requirements
- 4+ years of full-stack engineering experience.
- Strong problem-solving skills and ability to design elegant solutions.
- Experience working in fast-paced, product-driven environments or startups.
- Curiosity and willingness to explore how LLMs work at the architectural and implementation levels.
- Excellent communication, documentation, and cross-team collaboration skills.
Good To Have
- Experience with microservices architecture, Docker, and Kubernetes.
- Knowledge of authentication/authorization (OAuth, RBAC).
- Exposure to real-time systems, WebRTC, or streaming services.
- Experience building developer tools, internal platforms, or AI-powered workflows.
- Contribution to open-source projects is a strong plus.
This job was posted by Gokul Varma from Thinkhat.
