Company: Cosentus

Experience: 3–5 Years

Employment Type: Full-Time

About the RoleCosentus is looking for a Senior Full Stack & AI Platform Engineer with strong expertise in system design, scalable architecture, microservices, full-stack development, and AI-powered applications.

We are looking for a hands-on engineer who can independently design complex systems, develop application modules, integrate modern AI technologies, and take complete ownership from architecture through production.

A key challenge involves building scalable AI-powered healthcare applications capable of processing 2,000–5,000 medical charts within a 1–2 hour peak processing window, ensuring performance, reliability, accuracy, and cost efficiency.

The ideal candidate should be strong in Node.js, React.js, PostgreSQL, AWS Lambda, Amazon Bedrock, microservices, distributed systems, OCR, RAG, and practical AI/LLM implementation.

Key Responsibilities

- Design and develop scalable applications using React.js, Node.js, Express.js, TypeScript, PostgreSQL, and MongoDB.
- Own High-Level Design (HLD) and Low-Level Design (LLD) for complex modules, microservices, and distributed systems.
- Design high-throughput architectures using asynchronous processing, event-driven workflows, queues, caching, and parallel execution.
- Build and optimize AWS Lambda-based services and integrate AI models using Amazon Bedrock.
- Develop and scale AI/LLM workflows, OCR pipelines, Vision AI, structured data extraction, and RAG systems.
- Design scalable APIs, database schemas, background processing workflows, and communication between microservices.
- Implement concurrency controls, rate limiting, retries, idempotency, fault tolerance, and monitoring.
- Integrate AI agents, tool calling, and workflow orchestration where required.
- Identify and resolve performance bottlenecks across backend services, databases, AI models, and infrastructure.
- Take ownership of development, deployment, performance optimization, and production troubleshooting.

Core Technical Skills1.

Full Stack

Development & System DesignStrong hands-on experience with React.js, Node.js, Express.js, JavaScript, TypeScript, PostgreSQL, MongoDB, and REST APIs.

Strong understanding of

- HLD, LLD, scalable architecture, and microservices
- Distributed systems, event-driven architecture, and asynchronous processing
- Database design, query optimization,



and API architecture
- Concurrency, caching, load balancing, and horizontal scaling
- Authentication, authorization, security, and fault tolerance
- Performance optimization and architectural trade-offs

The candidate must be capable of converting business requirements into detailed, scalable technical designs and implementing them independently.

- Microservices, Distributed Systems & AWSStrong practical knowledge of microservices, distributed processing, asynchronous workflows, and event-driven system architecture.

Hands-on expertise with:
- AWS Lambda: Serverless development, deployment, concurrency, performance optimization, and scaling.
- Amazon Bedrock: Foundation model integration and production AI workflows.
- Working knowledge of AWS S3, SQS, API Gateway, CloudWatch, and IAM.

Experience with Redis, RabbitMQ, Kafka, or similar messaging and caching technologies. Understanding of worker concurrency, queue-based processing, retries, idempotency, rate limiting, failure recovery, observability, and cloud cost optimization.

Deep expertise across every AWS service is not required.

- AI / LLM Engineering, OCR & Document IntelligenceHands-on experience implementing production AI applications involving:

- LLM integration, prompt engineering, and context management.
- OCR, Vision AI, multimodal models, and PDF/image processing.
- Document classification, table/form extraction, and structured JSON outputs.
- Schema validation, error handling, and hallucination reduction.
- Multi-stage AI processing pipelines and model orchestration.
- Token optimization, AI latency management, and cost reduction.
- AI evaluation, accuracy improvement, and human-in-the-loop workflows.

The candidate should understand how to build reliable AI features beyond simply making LLM API calls.

- RAG & AI Workflow ArchitectureHands-on experience designing and implementing Retrieval-Augmented Generation (RAG) systems, including:

- Document ingestion, chunking, and embeddings




- Vector databases, semantic/hybrid search, and metadata filtering
- Retrieval optimization, reranking, and context construction
- Response grounding and RAG evaluation

Working knowledge of AI agents, function/tool calling, agent orchestration, state management, and contextual memory. Experience with LangChain, LangGraph, or similar frameworks is preferred.

- Scalability, Performance & Engineering OwnershipThe candidate should be capable of:

- Designing architectures for high-volume document and AI processing.
- Performing capacity planning, throughput estimation, and load testing.
- Building scalable background workers and asynchronous pipelines.
- Optimizing APIs, databases, model calls, and infrastructure.
- Troubleshooting complex production issues.
- Making architectural decisions and explaining technical trade-offs.
- Independently owning complex technical modules from requirements to deployment.

Good to Have
- Experience with US Healthcare, Revenue Cycle Management (RCM), medical coding, insurance claims, or HIPAA-aware applications.
- Advanced AI agents, multi-agent workflows, and agent orchestration.
- Knowledge graphs, graph-based retrieval, and advanced AI memory.
- Docker, CI/CD pipelines, and containerized deployments.
- Experience with AI evaluation frameworks and feedback-driven improvement systems.

Experience Required
- 3–5 years of professional software development experience.
- Strong full-stack development experience, particularly in backend engineering.
- Solid system design, microservices, and scalable architecture knowledge.
- Hands-on experience with AWS Lambda and Amazon Bedrock.
- Practical experience with AI/LLM integration, OCR, and RAG.
- Ability to independently design, implement, and own complex technical modules.

Ideal CandidateWe are looking for a hands-on engineer and strong system thinker who can take ownership of architecture, development, AI integration, scalability, and production reliability. The ideal candidate should be able to design distributed architectures, implement production-ready modules, optimize high-volume AI processing workflows, and solve complex engineering challenges independently.

- Our highest priorities are system design, scalable backend architecture, microservices, AWS Lambda, and practical AI implementation.

📌 Platform Engineer — Healthcare AI Platform USA (New Delhi)
🏢 Cosentus
📍 New Delhi