About Job:
AI Platform & Agentic Systems Engineer (AI / ML), Pune, India (Hybrid)
Experience- 5+ years
We are looking for a high-impact AI Platform & Agentic Systems Engineer who will help drive the AI transformation across our organization.
This role goes beyond traditional machine learning development. The engineer will design and build AI-powered platforms, intelligent agents, orchestration layers, and enterprise AI workflows that enhance productivity, automate processes, and unlock intelligence across systems and data.
You will work extensively with LLMs, SLMs, agentic AI architectures, vector databases, RAG pipelines, orchestration frameworks, and enterprise integrations to build scalable AI-enabled solutions.
The ideal candidate is someone who actively builds with AI, understands modern AI ecosystems deeply, and can convert AI capabilities into real-world production systems.
Key Responsibilities
Enterprise AI Platform Development
• Build and maintain internal AI platforms and services that enable teams across the organization to leverage AI capabilities
• Develop reusable AI APIs, SDKs, and microservices for enterprise adoption
• Integrate AI capabilities into existing systems, developer workflows, and business platforms
• Enable organization-wide adoption of AI-assisted workflows and automation
Agentic AI & Autonomous Systems
• Design and implement agent-based architectures capable of multi-step reasoning and task execution
• Build autonomous AI agents that interact with APIs, enterprise tools, and data systems
• Develop multi-agent systems capable of collaboration and workflow orchestration
• Implement tool-using agents that can dynamically select and use enterprise services
Examples may include:
- AI engineering assistants
- workflow automation agents
- data intelligence agents
- internal knowledge agents
AI Orchestration & Workflow Engines
• Design AI orchestration layers that coordinate models, tools, and workflows
• Build pipelines that manage:
o multi-step reasoning
o task decomposition
o tool execution
o memory and context management
• Work with orchestration frameworks such as:
o LangChain
o LlamaIndex
o CrewAI
o similar orchestration frameworks
• Enable structured interaction between LLMs, enterprise tools, APIs, and knowledge systems
LLM / SLM Systems
• Work with modern Large Language Models (LLMs) and Small Language Models (SLMs)
• Evaluate and select models based on:
o performance
o latency
o cost
o reliability
• Implement advanced techniques such as:
o prompt engineering
o prompt chaining
o context window management
o function calling
o tool invocation
Retrieval-Augmented Generation (RAG)
• Design and implement RAG architectures for enterprise knowledge retrieval
• Build pipelines that integrate LLMs with internal knowledge bases
• Optimize retrieval systems to improve contextual accuracy and response relevance
• Implement indexing pipelines and semantic retrieval strategies
Vector Databases & Knowledge Infrastructure
• Work with vector databases and embedding systems to enable semantic search
• Implement knowledge indexing pipelines using:
o Pinecone
o Weaviate
o Milvus
o Chroma
• Build scalable knowledge retrieval layers for AI applications
Machine Learning & AI Model Development
• Build ML pipelines using Python-based machine learning stacks
• Work with ML frameworks including:
o PyTorch
o TensorFlow
o Scikit-learn
o Hugging Face ecosystem
• Develop data pipelines, feature engineering workflows, and model training pipelines
• Evaluate model performance and experiment with different architectures
AI Infrastructure & Model Deployment
• Deploy AI workloads in cloud and containerized environments
• Build model inference pipelines and scalable AI services
• Work with infrastructure tools such as:
o Docker
o Kubernetes
o cloud AI platforms
• Implement monitoring, evaluation, and lifecycle management for AI systems
AI Development Environment & Tooling
• Work within AI-enabled development environments
• Leverage modern AI tooling including:
o VS Code AI ecosystem
o Copilot
o AI coding assistants
• Build internal tools that improve AI productivity across engineering teams
AI Safety, Guardrails & Evaluation
• Implement mechanisms to ensure safe and reliable AI outputs
• Build guardrails to reduce hallucinations and unsafe responses
• Develop AI evaluation frameworks and benchmarks
• Monitor AI system performance and continuously improve reliability
