Backend Developer

About Eka.Care

Eka.Care is building the healthcare infrastructure layer for India — a GenAI-powered platform trusted by millions of patients, doctors, and healthcare providers.

From EMRs to intelligent clinical workflows, Eka operates at the intersection of healthcare delivery and AI innovation. Hundreds of clinics, hospitals, and health platforms rely on Eka to power real-world healthcare operations.

Our next frontier is conversational AI agents — systems that can triage patients, manage appointments, and integrate seamlessly into healthcare workflows across WhatsApp, web, and mobile platforms. These are production-grade systems handling real users and real clinical scenarios — not prototypes.

We are looking for a Backend Developer who can bridge core backend engineering with modern AI systems . This role goes beyond traditional backend work — you’ll design scalable systems while also building and integrating LLM-powered pipelines, agentic workflows, and data-driven AI services .

If you’ve built backend systems and experimented with LLMs, RAG pipelines, or agent frameworks — this role is built for you.

What You’ll Do

Backend Engineering

Take end-to-end ownership of backend systems and services

Design, develop, and maintain scalable, high-performance architectures

Build and manage microservices with clean APIs and strong system design principles

Optimize applications for performance, scalability, and reliability

Write clean, maintainable, and well-tested code (unit + integration tests)

Collaborate with product and frontend teams to translate requirements into technical solutions

AI & Agent Systems

Build and integrate LLM-powered features and services into backend systems

Design agentic workflows using frameworks like LangChain, LangGraph, CrewAI, or custom orchestration

Implement tool-calling, memory handling, and reasoning loops for AI agents

Debug and trace model/agent behavior to improve reliability and outputs

RAG & Data Pipelines

Develop Retrieval-Augmented Generation (RAG) pipelines end-to-end

Work with vector databases, embeddings, and retrieval strategies

Improve system performance using recall/precision and retrieval quality metrics

Build data pipelines for ingestion, processing, and indexing

Evals, Experimentation & Optimization

Build and run LLM evaluation frameworks (automated + human-in-loop)

Track experiments with prompt versioning, logging, and regression analysis

Optimize prompts for accuracy, cost, and latency

Document and publish learnings via dashboards, reports, or notebooks

Core Requirements

2+ years of backend development experience

Strong proficiency in Python or GoLang

Solid understanding of Data Structures & Algorithms (DSA)

Experience with system design, APIs, and microservices architecture

Hands-on experience with SQL/NoSQL databases and query optimization

Experience building with LLM APIs (OpenAI, Anthropic, Gemini, or open-source models)

Working knowledge of:

Vector databases & embedding pipelines

At least one AI/agent framework (LangChain, LangGraph, CrewAI, AutoGen, etc.)

Familiarity with:

Messaging systems (queues/pub-sub)

REST APIs / RPC frameworks

Containerization (Docker, etc.)

What We’re Looking For

Strong problem-solving and analytical thinking

Ability to own systems end-to-end

Comfortable working in a fast-paced startup environment

Curiosity to explore and implement cutting-edge AI systems

Strong collaboration mindset with product and engineering teams

Bias for action and continuous learning

Employee Benefits

Insurance Benefits

Medical Insurance

Accidental Insurance

Parental Support

Maternity Benefit

Paternity Benefit Program

Mobility Benefits

Relocation Benefits

Transfer Support Policy

Retirement Benefits

Employee PF Contribution

Flexible PF Contribution

Gratuity

NPS

Leave Encashment

Other Benefits

Salary Advance Policy