Ai Ml Engineer

Agilisium; Pune District; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Agilisium in Pune is seeking a senior AI/ML engineer to design and deploy Generative AI and LLM-based applications. You will integrate LangChain, LangGraph, and RAG pipelines with FastAPI services, handling model selection, evaluation, and deployment.

The role requires 5+ years in AI/ML, strong Python, cloud experience, and hands-on work with vector databases, embeddings, and multi-agent workflows. Collaboration with data engineers, researchers, and product teams is essential.

Qualifications

• Bachelor's degree in Computer Science, Data Engineering, AI/ML, or a related field (Master's preferred).
• 5+ years of experience in AI/ML with hands-on Generative AI and LLM-based applications.

Responsibilities

• Develop and deploy Generative AI/LLM-based applications and services.
• Integrate LangChain, LangGraph, and RAG pipelines for AI agents and workflows.
• Build scalable AI solutions with FastAPI and cloud services.
• Collaborate with cross-functional teams to deliver production-grade AI systems.

Skills

Generative AI

LLMs

Python

LangChain

LangGraph

RAG

FastAPI

MLOps

Cloud platforms

Prompt engineering

Vector databases

SQL/NoSQL

Model deployment

Embeddings

Data ingestion

AI security

Team collaboration

Education

Bachelor's degree in CS/AI/related field

Master's preferred

Tools

Docker

Kubernetes

CI/CD

Hugging Face

Job description

Role & responsibilities

Generative AI | LLM | Python | LangChain | LangGraph | RAG | FastAPI

Must Have:

MCP | AI Agents | Vector Databases | LLM Fine-tuning | Cloud | MLOps | Life Sciences

Must-have skills:

• Bachelors degree in Computer Science, Data Engineering, AI/ML, or a related field (Master's preferred).
• 5+ years of experience in AI/ML, with significant hands-on experience in Generative AI and LLM-based applications.
• Strong hands-on experience with Generative AI / Large Language Models (LLMs), including model integration, evaluation, optimization, and deployment.
• Strong expertise in Python and experience building scalable AI applications and services.
• Hands-on experience with LangChain and LangGraph for developing LLM-powered applications, workflows, and AI agents.
• Strong experience building Retrieval-Augmented Generation (RAG) solutions, including document ingestion, chunking, embeddings, retrieval, reranking, context management, and response generation.
• Strong hands-on experience with FastAPI for developing and exposing AI/ML services and APIs.
• Experience working with LLM APIs and model providers such as OpenAI, Azure OpenAI, Hugging Face, Anthropic, Gemini, or equivalent.
• Good understanding of prompt engineering, embeddings, vector search, and LLM evaluation.
• Experience integrating GenAI solutions with SQL/NoSQL databases, vector databases, and enterprise data sources.
• Strong understanding of cloud platforms such as AWS, Azure, or GCP and their AI/ML services.
• Understanding of MLOps, model lifecycle management, deployment, monitoring, and productionization of AI solutions.
• Strong problem-solving, communication, and collaboration skills, with the ability to work with cross-functional teams.

Preferred Skills

• Model Context Protocol (MCP) experience, including building or integrating MCP servers/tools with LLM applications or AI agents.
• Experience developing AI Agents / Agentic AI workflows using LangGraph or similar frameworks.
• Experience with multi-agent systems, tool calling, function calling, and structured outputs.
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, Chroma, Milvus, or FAISS.
• Experience with LLM fine-tuning, LoRA/PEFT, or model optimization.
• Experience with Docker, Kubernetes, CI/CD, and cloud-native deployments.
• Strong understanding of AI security, data governance, responsible AI, and enterprise GenAI architecture.
• Life Sciences / Pharma / Healthcare domain expertise is highly desirable.
• Experience integrating GenAI solutions into production-level enterprise applications.