Full Stack Engineer

About Elimai.ai

Elimai.ai crafts AI-native solutions targeting critical challenges in healthcare and manufacturing by building intelligent automation pipelines. Our compact founding team develops impactful systems for actual clients, allowing engineers to visibly influence business success. This role offers an exceptional opportunity to create agentic AI solutions in production with full ownership of end-to-end systems.

Role Overview

As a full stack engineer, you'll be responsible for designing and delivering AI-driven full-stack systems. Your scope includes the API layer, data modeling, agent orchestration, and front-end interfaces. With significant autonomy, you will make architectural decisions, integrate large and small language model workflows, and advance features from conceptual stages to production deployments. You will collaborate directly with founders and AI experts, ensuring rapid transition from ideas to working code.

Key Projects

• Develop production-grade agentic workflows involving multi-step, tool-utilizing agents that handle classification, extraction, summarization, and action on real-world datasets such as documents, emails, claims, and images.
• Create AI-powered backend services with event-driven architectures including queues, asynchronous workers, and webhooks to orchestrate tasks across different types of language models and deterministic logic.
• Implement MCP protocol servers and utilities that offer clean, reusable access to internal systems and data for agents.
• Build comprehensive full-stack features including RESTful APIs, database schemas, and React/Next.js front-end applications to make AI intelligence accessible.
• Optimize inference processes for cost and latency by selecting appropriate models, utilizing prompt caching, model routing, and fallback mechanisms.

Required Technical Skills

• Minimum two years of experience developing production software as a backend or full-stack engineer.
• Proficiency in Python (FastAPI framework) and MERN stack; strong skills in React and Next.js preferred.
• Expertise in designing REST APIs and implementing asynchronous processing with queue systems such as SQS, RabbitMQ, or Kafka.
• Database proficiency with PostgreSQL and at least one NoSQL/document database like MongoDB or DynamoDB, including data modeling and indexing for scalable workloads.
• Practical experience working with AWS services (EC2, S3, Lambda, RDS/DynamoDB), containerization technologies like Docker, and CI/CD pipelines; Kubernetes knowledge is advantageous.
• Commitment to writing clean, maintainable, and well-tested code alongside calm troubleshooting during production incidents.

AI-Focused Engineering Expertise

• Familiarity with large language model development techniques including prompt engineering, function/tool invocation, structured JSON outputs, and streaming data handling.
• Hands-on experience with agent orchestration SDKs such as Anthropic Agent SDK, OpenAI Agents SDK, LangGraph, or similar frameworks, including multi-agent routing and tool integration.
• Building or consuming Model Context Protocol (MCP) servers to connect agents with tools and data sources effectively.
• Competence in retrieval-augmented generation (RAG) strategies and vector search using embedding databases like Pinecone, Weaviate, pgvector, or FAISS with an emphasis on retrieval accuracy.
• Exposure to small language model (SLM) development involving fine-tuning, evaluation, and deployment of open or lightweight models (e.g., Llama, Qwen, Gemma, Phi) for performance-sensitive tasks, including on-device or self-hosted inference.
• Experience implementing reliability measures such as guardrails, hallucination control, validation and retry mechanisms, and evaluation frameworks treating AI systems as testable entities.
• Good judgment in balancing cost and latency with model choices, routing strategies, fallbacks, and prompt caching approaches.

Preferred Qualifications

• Background working with healthcare or manufacturing datasets, especially in regulated or compliance-focused settings.
• Experience in Document AI domains including OCR, layout analysis, and vision-language model extraction pipelines.
• Knowledge of observability tools for AI systems such as tracing, token/cost monitoring, and prompt/version control.
• Contributions to open-source AI projects or evidence of shipping agentic AI software products.

Compensation and Work Arrangement

The offered salary range is ₹15,000,000 to ₹18,000,000 per annum based on experience, accompanied by meaningful equity participation (ESOPs) in this early-stage company that values impact-driven contributions. The position supports hybrid work from Coimbatore or fully remote arrangements.