Application Support Engineer

codingcircle; Mumbai; On-site; INR 500,000 - 800,000; Full time

Job summary

codingcircle is looking for an Application Support Engineer to work in Mumbai. This role involves designing Generative AI applications, implementing RAG pipelines, and developing scalable microservices. The ideal candidate should have strong skills in Python and relevant AI technologies, along with a B.Tech / M.Tech in Computer Science or related fields.

Experience in full-stack development and knowledge of LLM evaluation techniques are preferred, along with a creative and experimental mindset.

Qualifications

• 0-2 years of experience in relevant role.
• 15 years full-time education required.
• Experience with AI projects, especially GenAI preferred.

Responsibilities

• Design and develop Generative AI applications using specified frameworks.
• Build and implement RAG pipelines for enterprise systems.
• Translate functional requirements into technical designs.

Skills

Python

AI & GenAI

LangChain

LangGraph

RAG pipeline implementation

LLM inferencing pipelines

Agentic AI workflows

NestJS (Node.js framework)

Vector Databases (pgVector, OpenSearch, Milvus)

PostgreSQL

AWS RDS

REST APIs

Git-based development workflows

Knowledge of LLM evaluation techniques

MLOps / LLMOps practices

Education

B.Tech / M.Tech / Equivalent in Computer Science, AI, Data Science, or related fields

Tools

Draw.io

Apache Spark

AWS

GCP

Job description

Job Description

Company : Accenture

Project Role : Application Support Engineer

Job No : ATCI-5490974-S2002795

Job Type : Full time

Required Skill : Python (Programming Language)

Experience : 0-2 years

Educational Qualification : 15 years full time education

Location : Mumbai

Responsibilities

• Design and develop Generative AI applications using LangChain and LangGraph frameworks.
• Build RAG (Retrieval Augmented Generation) pipelines for enterprise knowledge systems.
• Develop agentic AI workflows and orchestration pipelines using LangGraph.
• Implement LLM inferencing pipelines using open-source or enterprise models.
• Build AI pipelines for document ingestion, embedding, vector search, and response generation.
• Experiment with emerging AI standards and protocols such as MCP (Model Context Protocol).
• Develop scalable microservices using NestJS and Python.
• Design and build REST APIs with secure programming practices.
• Implement event-driven integrations using webhooks and asynchronous messaging patterns.
• Develop DAG-based workflows and data pipelines.
• Implement vector search and semantic retrieval pipelines using pgVector, AWS OpenSearch, or Milvus.
• Design and manage metadata stores using PostgreSQL or AWS RDS.
• Work with Apache Spark or distributed data processing frameworks for large-scale data pipelines.
• Build and deploy applications on AWS or GCP cloud platforms.
• Implement scalable AI application architectures using containerized workloads, Docker, Kubernetes, AWS app services (incl. AWS Bedrock), and Managed database services.
• Work with cloud-native services for AI model hosting and orchestration.
• Implement secure API design based on OWASP API Security guidelines.
• Follow secure coding practices and data privacy guidelines.
• Ensure observability, logging, and error handling in production systems.
• Translate functional requirements into technical designs and implementation plans.
• Design RAG pipelines and Agentic AI flows using LangGraph DAG-based orchestration.
• Create architecture diagrams and solution documentation using draw.io.

Required Technical Skills

• AI & GenAI
• LangChain
• LangGraph
• RAG pipeline implementation
• LLM inferencing pipelines
• Agentic AI workflows
• Python
• NestJS (Node.js framework)
• Vector Databases (pgVector, OpenSearch, Milvus)
• PostgreSQL
• AWS RDS
• REST APIs
• Webhooks
• Secure API design
• OWASP API security standards
• DAG-based workflows
• Apache Spark (basic)
• AWS or GCP
• draw.io
• Git-based development workflows
• Knowledge of LLM evaluation techniques
• Experience with embedding models and semantic search
• Experience with LLM observability and prompt engineering
• Understanding of agent orchestration patterns and multi-agent systems
• Exposure to MLOps / LLMOps practices
• Conceptual DevOps knowledge

Professional & Technical Skills

• Hands‑on implementation experience in at least one of the following:
  • RAG-based knowledge assistant
  • LLM inferencing application
  • Agentic AI workflow using LangChain or LangGraph
  • Document ingestion and vector search pipeline
• Strong analytical and problem‑solving skills
• Ability to quickly learn new technologies and frameworks
• Experimental mindset with innovation and prototyping capability
• Strong communication and documentation skills
• Ability to translate functional requirements into technical architecture

Additional Information

• The candidate should have minimum 2 years of experience in Java Full Stack Development.
• B.Tech / M.Tech / Equivalent in Computer Science, AI, Data Science, or related fields.
• Candidates who have built GenAI projects during final year, internship, or industry experience will be preferred.
• This position is based at our Mumbai office.
• A 15 years full time education is required.