Full Stack Developer :: Acon
India · Mid Level
Applicants who checked fit first are 3.1× more likely to hear back
Your score for this role already exists
ASAI compared this JD against 41 signals - skills, seniority, domain, stack overlap etc. Add a resume and it unlocks in about 30 seconds.
No credit card · 1 tap with Google
What we know about this role
HIGH
KPMG India is actively reviewing profiles and moving candidates through the pipeline right now.
First 72 hours
Still inside it - posted 1h agoEarly applicants get seen before the pile builds.
Reposted role
This role was posted earlier, closed, and has now reopened - the company is accepting candidates again.
First posted Jul 24, 2026
Skills required
27 listedYou almost certainly match several of these already. Unlock your skill map to see the matches, the gaps, and what to fix first.
Job description
Responsible for designing, developing, and deploying scalable Generative AI solutions using state-of-the-art large language models (LLMs) and transformer architectures.
- Responsible for building out sophisticated AI agent workflows, establishing a scalable cloud infrastructure, and ensuring the application can handle large- scale document ingestion and concurrent user requests seamlessly.
- Design and implement highly complex Retrieval-Augmented Generation (RAG) systems, specifically focusing on Agentic RAG (autonomous decision-making workflows) and Multimodal RAG (handling text, images, and other data types).
Backend Development & Orchestration: Build robust, high-performance APIs and backend services using Python and FastAPI. Orchestrate complex LLM workflows and agents utilizing LangChain and LangGraph.
- Search & Data Infrastructure: Develop data ingestion pipelines capable of handling exceptionally large documents. Configure, optimize, and maintain Vector Databases and Azure AI Search for low-latency, high-accuracy retrieval
- Frontend & UI Development: Develop rapid, functional, and interactive user interfaces using Streamlit. Utilize JavaScript to build custom frontend components, integrate web elements, and enhance the overall user experience.
- DevOps & Automation: Establish, maintain, and optimize CI/CD pipelines to ensure smooth, automated testing, building, and deployment of the GenAI application.
Document Processing: Handson in parsing complex financial documents, unstructured enterprise documents (PDFs, PPTs, tables, Excel, Word, txt, charts, images etc)
Required Skills
- Programming Languages: Deep expertise in Python; solid working knowledge of JavaScript.
- Strong experience with Azure OpenAI, Azure Machine Learning, Cognitive Search, and AI Studio.
- Solid understanding of LLMs, embeddings, RAG pipelines, vector search, prompt engineering.
- GenAI & LLM Frameworks: Extensive hands-on experience with LangChain and LangGraph/ Semantic Kernel / LlamaIndex. Proven ability to build beyond basic RAG into Agentic and Multimodal implementations.
- Backend & APIs: Strong experience building scalable RESTful APIs with FastAPI.
- Cloud & DevOps (Azure): Demonstrated experience deploying enterprise-grade applications on Azure. Deep understanding of Docker, containerization, and configuring automated CI/CD pipelines.
- LLM Evaluation & Observability: Hands-on experience with evaluation frameworks (e.g., RAGAS, TruLens, DeepEval) and monitoring/tracing tools (e.g., LangSmith, Langfuse, Arize Phoenix).
- Databases & Search: Practical experience with Azure AI Search and leading Vector Databases (e.g., Pinecone, Milvus, Qdrant, or Azure Native).
- System Architecture: Proven track record of designing systems for parallelism, large-scale data ingestion, and multi-user environments (SaaS architecture).
- Frontend/Prototyping: Experience building responsive interfaces using Streamlit,HTML,CSS,Javascript.
- Docker, Kubernetes (for model deployment)
- Previous experience building commercial AI products or complex advisory/analytical AI agents from the ground up.
- Strong understanding of data security and tenant isolation in cloud environments.
- Understanding of responsible AI, data privacy, and application security, Guardrails.
- Fine-tune and customize foundation models using domain-specific datasets and techniques.
Responsible for designing, developing, and deploying scalable Generative AI solutions using state-of-the-art large language models (LLMs) and transformer architectures.
- Responsible for building out sophisticated AI agent workflows, establishing a scalable cloud infrastructure, and ensuring the application can handle large- scale document ingestion and concurrent user requests seamlessly.
- Design and implement highly complex Retrieval-Augmented Generation (RAG) systems, specifically focusing on Agentic RAG (autonomous decision-making workflows) and Multimodal RAG (handling text, images, and other data types).
Backend Development & Orchestration: Build robust, high-performance APIs and backend services using Python and FastAPI. Orchestrate complex LLM workflows and agents utilizing LangChain and LangGraph.
- Search & Data Infrastructure: Develop data ingestion pipelines capable of handling exceptionally large documents. Configure, optimize, and maintain Vector Databases and Azure AI Search for low-latency, high-accuracy retrieval
- Frontend & UI Development: Develop rapid, functional, and interactive user interfaces using Streamlit. Utilize JavaScript to build custom frontend components, integrate web elements, and enhance the overall user experience.
- DevOps & Automation: Establish, maintain, and optimize CI/CD pipelines to ensure smooth, automated testing, building, and deployment of the GenAI application.
Document Processing: Handson in parsing complex financial documents, unstructured enterprise documents (PDFs, PPTs, tables, Excel, Word, txt, charts, images etc)
Required Skills
- Programming Languages: Deep expertise in Python; solid working knowledge of JavaScript.
- Strong experience with Azure OpenAI, Azure Machine Learning, Cognitive Search, and AI Studio.
- Solid understanding of LLMs, embeddings, RAG pipelines, vector search, prompt engineering.
- GenAI & LLM Frameworks: Extensive hands-on experience with LangChain and LangGraph/ Semantic Kernel / LlamaIndex. Proven ability to build beyond basic RAG into Agentic and Multimodal implementations.
- Backend & APIs: Strong experience building scalable RESTful APIs with FastAPI.
- Cloud & DevOps (Azure): Demonstrated experience deploying enterprise-grade applications on Azure. Deep understanding of Docker, containerization, and configuring automated CI/CD pipelines.
- LLM Evaluation & Observability: Hands-on experience with evaluation frameworks (e.g., RAGAS, TruLens, DeepEval) and monitoring/tracing tools (e.g., LangSmith, Langfuse, Arize Phoenix).
- Databases & Search: Practical experience with Azure AI Search and leading Vector Databases (e.g., Pinecone, Milvus, Qdrant, or Azure Native).
- System Architecture: Proven track record of designing systems for parallelism, large-scale data ingestion, and multi-user environments (SaaS architecture).
- Frontend/Prototyping: Experience building responsive interfaces using Streamlit,HTML,CSS,Javascript.
- Docker, Kubernetes (for model deployment)
- Previous experience building commercial AI products or complex advisory/analytical AI agents from the ground up.
- Strong understanding of data security and tenant isolation in cloud environments.
- Understanding of responsible AI, data privacy, and application security, Guardrails.
- Fine-tune and customize foundation models using domain-specific datasets and techniques.
BTech / Mtech / IT
Free · no signup
Get tomorrow's jobs before you have to search
Daily job drops, skill trends and free resources - posted straight to the group. Leave any time.
No spam. Just jobs and resources.
Why people use ASAI
Someone shared one job with you. ASAI keeps finding the rest.
Scored, not searched. Every role ranked against your actual profile.
Alerts as often as hourly. Reach new roles while the pile is still small.
Skill gaps, spelled out. See exactly which requirements you don't meet yet.
Verified jobs, only. Say no to ghost jobs. Your time deserves respect.
Keep browsing