Backend Engineer (AI / LLM / Claude Applications)

Althera Laboratories
Posted on
Experience
3 - 7 yrs
Job Location
Bengaluru, India
Vacancy
2
Designation
Back End Engineer
Job Type
Not specified

Job Description

Job Title: Backend Engineer (AI / LLM / Claude Applications)


Role Overview

We are looking for a skilled Backend Engineer to design, build, and scale backend systems for AI-powered applications, with a strong focus on Claude (Anthropic) / LLM-based solutions. You will work closely with AI/ML engineers, frontend developers, and product teams to integrate large language models into production-grade systems.


Key Responsibilities

  • Design and develop scalable backend systems and APIs for AI-driven applications
  • Integrate Claude API (Anthropic) and other LLMs (OpenAI, Azure OpenAI, etc.) into products
  • Build middleware, orchestration layers, and agent frameworks for AI workflows
  • Implement prompt pipelines, context management, and memory systems
  • Develop high-performance REST/GraphQL APIs for AI services
  • Handle real-time and asynchronous processing of AI inference workflows
  • Optimize latency, cost, and throughput for LLM usage
  • Implement RAG (Retrieval Augmented Generation) pipelines using vector databases
  • Ensure security, compliance, and data privacy standards for AI systems
  • Monitor and maintain production systems, logging, and observability
  • Collaborate with DevOps for CI/CD, containerization, and cloud deployment

Required Skills & Qualifications

Core Backend Skills

  • Strong experience in Python / Node.js / Java / Go
  • Expertise in building scalable microservices architecture
  • Solid understanding of REST APIs, GraphQL, and distributed systems
  • Experience with databases: SQL PostgreSQL, MySQL), NoSQL (MongoDB, Redis, DynamoDB)

AI / LLM Experience - Claude API (Anthropic) preferred, OpenAI / Azure OpenAI / other LLMs

  • Understanding of Prompt engineering, Token management & Context window optimization
  • Experience building:

Chatbots, copilots, or AI agents

Data & AI Infrastructure

  • Experience with vector databases:

Pinecone, Weaviate, FAISS, Chroma

  • Knowledge of RAG architectures
  • Familiarity with embedding models and semantic search

Cloud & DevOps

  • Experience with cloud platforms: Azure / AWS / GCP
  • Knowledge of Docker, Kubernetes, CI/CD pipelines, Serverless architectures

No Referrers Available

There are currently no referrers available for this job. You can still apply, will let you know once there is any referrer available.