Position : Senior AI/ML Engineer

Note : Apply only if you can start immediately / 2-3 weeks of notice period.

Company Overview :

Prama.ai specializes in AI-powered and Generative AI solutions across Data, Cloud, and APIs, helping businesses build intelligent platforms and scalable AI-driven products.

With 500+ projects delivered globally and 30+ engagements currently in progress, Prama.ai brings deep expertise in Data Engineering, AI/ML, and Advanced Analytics across industries such as SaaS, FinTech, Healthcare, and EdTech. We have also built 6 proprietary products, reflecting our strong product engineering DNA.

Finomics.ai is Prama.ai's in-house financial intelligence and analytics platform, reinforcing our commitment to building practical, real-world solutions that deliver measurable business impact.

Prama.ai is ISO 27001 certified and SOC 2 Type II compliant, demonstrating our strong commitment to security and compliance. We are a trusted partner with AWS, Google Cloud Platform (GCP), Snowflake, and Databricks.

Headquartered in Phoenix, Prama.ai operates globally with offices in the USA (Chandler, AZ), Canada (Toronto), and India (Ahmedabad and Bangalore).

Job Location : Bangalore (Hybrid)

Experience : 3 - 5+ years

Primary Skills : Langchain, RAG, ML, Azure AI Foundry, Python, AI/ML workflows

Role Summary :

We are seeking a Senior AI/ML Engineer to build, optimize, and deploy production-grade Generative AI and Machine Learning applications. In this role, you will design advanced Retrieval-Augmented Generation (RAG) systems and build intelligent agentic workflows using Python and Azure AI Foundry. You will turn raw models into reliable, high-performance services that integrate with our existing infrastructure.

Key Responsibilities :

- RAG & Search Optimization : Architect and fine-tune end-to-end RAG pipelines (document processing, vector embeddings, hybrid search, reranking, and context compression) to ensure grounded, low-latency AI responses.

- Agentic Workflows : Implement multi-step agentic systems and tool-calling mechanisms using LangChain (or LlamaIndex/Semantic Kernel) integrated into Azure AI Foundry.

- Model Deployment & Integration : Deploy, evaluate, and manage LLMs and traditional ML models using Python-based microservices and Azure AI services.

- Evaluation & Observability : Implement continuous evaluation frameworks (hallucination checks, groundedness metrics, toxicity filters) and set up tracing using Azure AI evaluation tools.

- MLOps & Pipeline Engineering : Maintain automated workflows for model ingestion, prompt management, and deployment pipelines using Azure DevOps or GitHub Actions.

Required Qualifications :

- Experience : 3 - 5+ years in Software/ML Engineering with a strong focus on Generative AI and NLP.

- Core Tech Stack :

- Languages : Advanced Python (AsyncIO, FastAPI/Flask, Pydantic, Pandas, NumPy).

- Frameworks : LangChain, LlamaIndex, or Microsoft Semantic Kernel.

- Cloud Platform : Azure AI Foundry (Azure OpenAI Service, Azure AI Search, Prompt Flow, Agent Service).

- Database & Vector Search : Azure AI Search, Qdrant, Pinecone, or PGVector.

- Knowledge : Deep understanding of transformer architectures, tokenization, prompt engineering, and context window optimization.