Build and maintain Python-based Generative AI applications and RAG pipelines. Implement and optimize LLMs (GPT, LLaMA, Mistral, FLAN T5), embeddings, indexing, chunking, reranking, prompts, and evaluation. Integrate multiple data sources, use cloud GPU resources (AWS/Azure/Databricks), design agentic/multi-agent systems with LangGraph/CrewAI/AutoGen, collaborate across teams, document specifications, and assist in delivering client solutions.
Key Responsibilities:
- 5+ years of experience as a NLP and Python developer.
- Experience with Pandas, NumPy, Scikit, NLP a must have
- Key fundamentals in object-oriented design, data structures and systems.
- Ability to integrate multiple data sources into a single system.
- Familiarity with testing tools.
- Ability to collaborate on projects and work independently when required.
- Working knowledge of GitHub and Jira
- Ability to document requirements and specifications.
- Develop and maintain advanced Python-based applications in the Generative AI domain, ensuring high performance, reliability, and scalability.
- Implement and optimize Generative AI models, including GPT, LLAMA, Mistral, FLAN T5 and other cutting-edge AI technologies, to create innovative solutions and knowledge graph.
- Development of advanced RAG pipelines with proper embeddings, indexing, chunking, reranking, prompts and evaluation
- Collaborate with cross-functional teams to integrate AI functionalities into broader systems and applications.
- Utilize AWS/Azure/Databricks GPU machines to manage GPU memory effectively, maximizing performance and efficiency.
- Stay updated on the latest advancements in Generative AI, Python development practices, and cloud services to continually enhance our AI capabilities.
- Assist delivery leads in delivering Generative AI solutions to clients in a timely manner, ensuring client satisfaction and project success.
- Design and develop Agentic AI and Multi-Agent Systems leveraging frameworks such as LangGraph, CrewAI, AutoGen, to enable autonomous reasoning, orchestration, task execution, and enterprise workflow automation.
Required Skills and Experience:
- Bachelor's or Master's degree in a quantitative field (CS, machine learning, mathematics, statistics) or equivalent experience.
- 5+ years of experience in data science, building hands-on ML models.
- Candidate must be aware of entire evolution history of NLP (Traditional Language Models to Modern Large Language Models), training data creation, training set-up and finetuning
- Knowledge of advanced RAG pipelines with proper embeddings, indexing, chunking, reranking, prompts and evaluation
- Excellent programming skills in Python. Strong working knowledge of Pythons numerical, data analysis, or AI frameworks such as NumPy, Pandas, Scikit-learn, Jupyter, etc
- SQL skills with SQL Server and Spark experience is preferred but not necessary.
- Knowledge of predictive/prescriptive analytics including Machine Learning algorithms (Supervised and Unsupervised) and deep learning algorithms and Artificial Neural Networks
- Experience with Natural Language Processing (NLTK) and text analytics for information extraction, parsing and topic modeling.
- Excellent verbal and written communication. Strong troubleshooting and problem-solving skills. Thrive in a fast-paced, innovative environment
- Experience with cloud platforms such as Azure, AWS, Databricks is preferred
Key Responsibilities:
- 5+ years of experience as a NLP and Python developer.
- Experience with Pandas, NumPy, Scikit, NLP a must have
- Key fundamentals in object-oriented design, data structures and systems.
- Ability to integrate multiple data sources into a single system.
- Familiarity with testing tools.
- Ability to collaborate on projects and work independently when required.
- Working knowledge of GitHub and Jira
- Ability to document requirements and specifications.
- Develop and maintain advanced Python-based applications in the Generative AI domain, ensuring high performance, reliability, and scalability.
- Implement and optimize Generative AI models, including GPT, LLAMA, Mistral, FLAN T5 and other cutting-edge AI technologies, to create innovative solutions and knowledge graph.
- Development of advanced RAG pipelines with proper embeddings, indexing, chunking, reranking, prompts and evaluation
- Collaborate with cross-functional teams to integrate AI functionalities into broader systems and applications.
- Utilize AWS/Azure/Databricks GPU machines to manage GPU memory effectively, maximizing performance and efficiency.
- Stay updated on the latest advancements in Generative AI, Python development practices, and cloud services to continually enhance our AI capabilities.
- Assist delivery leads in delivering Generative AI solutions to clients in a timely manner, ensuring client satisfaction and project success.
- Design and develop Agentic AI and Multi-Agent Systems leveraging frameworks such as LangGraph, CrewAI, AutoGen, to enable autonomous reasoning, orchestration, task execution, and enterprise workflow automation.
Bachelor's or Master's degree in a quantitative field (CS, machine learning, mathematics, statistics) or equivalent experience.
Similar Jobs
Fintech • Financial Services
Design, build, and implement AI agents and agentic workflows within CI/CD on AWS. Engineer RAG pipelines (SageMaker + Lambda), develop MCP server integrations, leverage LLMs (OpenAI, Bedrock), vector databases, and code-generation tooling. Integrate with CI/CD and security tools; ensure application security and deploy using container orchestration (ECS/EKS).
Top Skills:
Api GatewayApplication SecurityAws LambdaBedrockCi/CdDockerEcsEksGenaiGitHarnessJenkinsKubernetesLlmsMcp ServerOpenaiPythonRag PipelineS3SagemakerSnykSonarqubeVector Databases
Artificial Intelligence • HR Tech • Professional Services • Software
Design, build, and deploy agentic Generative AI solutions and end-to-end ML pipelines. Perform prompt engineering, model integration (OpenAI, Llama family, Azure OpenAI), vector search, and productionization. Collaborate with customers, produce solution designs, and apply ML best practices for recommendation, deep learning, and NLP use cases.
Top Skills:
Azure OpenaiCnnEmbedding ModelsLangchainLanggraphLlamaLlama2Ml PipelinesNlp LibrariesOpenaiPrompt EngineeringPythonPyTorchScikit-LearnTensorFlowTransformersVector Databases
Artificial Intelligence • Information Technology • Machine Learning • Software • Virtual Reality • Analytics
Lead architecture and delivery of AI-powered user-facing applications using Python and React. Design scalable backend platforms for LLM inference, RAG pipelines, and agent orchestration. Define frontend UX for conversational interfaces, establish GenAI best practices, build reusable platform components, ensure enterprise readiness (security, privacy, governance), and mentor engineering teams.
Top Skills:
Agent-Based OrchestrationAWSAzureClaude CodeCopilotDistributed SystemsGCPGenerative AiLlmLlm InferenceModel IntegrationObservabilityPrompt DesignPythonReactRetrieval-Augmented Generation (Rag)
What you need to know about the Mumbai Tech Scene
From haggling for the best price at Chor Bazaar to the bustle of Crawford Market, the energy of Mumbai's traditional markets is a key part of the city's charm. And while these markets will always have their place, the city also boasts a thriving e-commerce scene, ranking among the largest in the region. Driven by online sales in everything from snacks to licensed sports merchandise to children's apparel, the local industry is worth billions, with companies actively recruiting to meet the demands of continued growth.
