Custom Software Engineer

We Love AI Jobs; Mumbai; On-site; INR 3,500,000 - 5,500,000; Full time

Job summary

We Love AI Jobs is seeking a Custom Software Engineer to build enterprise-grade GenAI applications in Mumbai. You will work on Python-based solutions utilizing LLMs, RAG, and semantic search, integrating AI models with existing systems, and contributing to architecture decisions.

The role emphasizes hands-on LLM integration, scalable data pipelines, and collaboration with the team to deliver high-performing AI-powered capabilities on-site in Mumbai.

Qualifications

• Must have Python experience for enterprise-grade GenAI applications.
• Hands-on experience with LLMs, RAG and vector databases.
• Knowledge of emerging AI frameworks and tooling.

Responsibilities

• Design, develop, and maintain AI-powered Python applications.
• Build GenAI solutions with LLMs, RAG, and semantic search.
• Develop data ingestion pipelines and integrate AI models with enterprise apps.
• Monitor performance and contribute to architectural decisions.

Skills

Python

LLM integration

RAG

Agentic AI workflows

Vector search

LangChain

FastAPI

Hugging Face Transformers

Education

15 years full time education

Tools

Git

Docker

Kubernetes

Grafana

CI/CD

Job description

# Custom Software EngineerAccenture Federal ServicesMumbaiFull-timeAI tools:OpenAIGeminiAnthropicLangChainLangGraphHugging FaceSentence TransformersFAISSUpload your resume once and Scout applies for youApply with ScoutShare this job:LinkedInXSave imageYou will build Python-based enterprise applications that use generative AI, language models, and retrieval to support search and other business workflows. The role also covers data pipelines, model integrations, and monitoring, with contributions to architecture and team guidance.* Full-time* On-site* 3+ years* 15 years of full-time education### Skills and expertisePythonLLM integrationRAGAgentic AI workflowsVector searchLangChainFastAPIHugging Face Transformers### Key responsibilities* Develop Python applications using LLMs, RAG, semantic search, and agentic workflows.* Build scalable data ingestion pipelines and integrate AI models with enterprise applications.* Monitor and optimize AI application performance and contribute to architecture decisions.## How this job comparesCompared with 329 open mid-level machine learning jobs on October 10, 2026.Similar open jobs: We Love AI Jobs lists 329 open mid-level machine learning jobs at 145 companies.Remote work: This job is on site. 66 of the 329 mid-level machine learning jobs (20%) are remote.AI in this role: High. AI is the core of the work: building, training or deploying AI systems. Building and optimizing GenAI applications, RAG pipelines, and agentic workflows are central responsibilities. The posting specifically requires hands-on LLM integration and AI application development.## Full descriptionProject Role : Custom Software EngineerProject Role Description : Develop custom software solutions to design, code, and enhance components across systems or applications. Use modern frameworks and agile practices to deliver scalable, high-performing solutions tailored to specific business needs.Must have skills : Python (Programming Language)Good to have skills : AI & Data Solution ArchitectureMinimum 3 year(s) of experience is requiredEducational Qualification : 15 years full time educationSummarySeeking an experienced Python + AI-GenAI Engineer with expertise in building enterprise-grade GenAI applications, intelligent search solutions, Agentic AI workflows, and scalable data processing pipelines. The ideal candidate should have hands-on experience with LLMs, RAG, Vector Databases, and modern AI frameworks.Experience4+ years of Python development experience2+ years of AI-GenAI-RAG and LLM application developmentRoles & ResponsibilitiesDesign, develop, and maintain AI-powered applications using Python.Build enterprise GenAI solutions leveraging LLMs and Natural Language Interfaces.Develop and optimize RAG, Text-to-SQL, Semantic Search, and Agentic AI solutions.Design and implement scalable data ingestion and processing pipelines.Integrate AI models with enterprise applications and APIs.Monitor, troubleshoot, and optimize AI application performance.Contribute to architecture decisions and mentor team members.Must Have SkillsPython, OOPs, Design Patterns, Unit TestingFastAPI, Flask, Django REST FrameworkSQL, Data Modeling, Shell ScriptingPandas, NumPy, DataFramesAuthentication & Authorization (JWT-OAuth-SSO)LLM Integration (OpenAI, Gemini, Anthropic, or similar)Vector Search, Semantic Search, Agentic AI WorkflowsGenAI Tooling and Natural Language Interface DevelopmentRAG Pipeline Development & OptimizationText-to-SQL SystemsLangChain, LangGraph, Sentence TransformersHugging Face TransformersEmbedding Models (OpenAI, BERT, or similar)Vector Databases (FAISS, Qdrant, Weaviate, or similar)Create and manage Embeddings and Vector StoresGrafana Monitoring & ObservabilityGit, CI-CDGood to HaveAzure OpenAI, AWS BedrockLlamaIndex, MCPDocker, KubernetesAWS-Azure CloudUpload your resume once and Scout applies for youApply with Scout