Job Title: Senior AI/ML Engineer – Generative AI & Agentic AI
Job Summary
We are seeking an experienced Senior AI/ML Engineer with 7–10 years of experience in Artificial Intelligence, Machine Learning, and Generative AI to design and build enterprise-scale AI solutions. The ideal candidate will have extensive hands-on expertise in Large Language Models (LLMs), Agentic AI frameworks, Retrieval-Augmented Generation (RAG), Prompt Engineering, LLMOps, and cloud AI platforms.
The role involves architecting and developing production-ready AI applications, autonomous AI agents, intelligent workflows, and scalable cloud-native AI services while collaborating with cross-functional engineering, product, and business teams.
Key Responsibilities
Generative AI & Large Language Models
- Design, develop, and deploy enterprise-grade Generative AI applications using modern LLMs.
- Build intelligent AI assistants, copilots, chatbots, and knowledge management solutions.
- Develop scalable Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge retrieval.
- Optimize LLM performance using Prompt Engineering, prompt tuning, grounding, and evaluation techniques.
- Fine-tune and integrate open-source and commercial LLMs where required.
- Implement AI safety, guardrails, content moderation, and responsible AI practices.
Agentic AI Development
- Design and develop autonomous AI agents capable of planning, reasoning, memory management, and tool usage.
- Build multi-agent orchestration systems using:
- LangGraph
- CrewAI
- LangChain Agents
- Implement agent workflows, state management, memory, and long-running execution pipelines.
- Develop AI agents capable of interacting with enterprise APIs, databases, and external tools.
- Build event-driven and workflow-based autonomous AI systems.
LangChain & LangGraph
- Develop modular AI workflows using LangChain.
- Build graph-based reasoning systems using LangGraph.
- Implement:
- Chains
- Tools
- Retrievers
- Memory
- Custom Agents
- Multi-agent orchestration
- Integrate external enterprise systems through tool calling.
Model Context Protocol (MCP)
- Design and implement AI applications using Model Context Protocol (MCP).
- Build secure integrations between AI models and enterprise tools.
- Develop reusable MCP servers and clients.
- Enable context-aware AI interactions across enterprise systems.
Retrieval-Augmented Generation (RAG)
- Design enterprise RAG architectures.
- Build semantic search systems using embeddings and vector databases.
- Implement:
- Document ingestion
- Chunking
- Metadata extraction
- Embedding pipelines
- Hybrid search
- Re-ranking
- Optimize retrieval quality and response accuracy.
Vector Databases
Develop scalable semantic search solutions using:
- Pinecone
- ChromaDB
- Weaviate
- FAISS
Implement:
- Embedding storage
- Similarity search
- Hybrid search
- Metadata filtering
- Index optimization
Python Development
- Build scalable backend AI services using Python.
- Develop reusable AI frameworks and libraries.
- Build REST APIs using FastAPI.
- Optimize inference pipelines for performance and scalability.
- Implement asynchronous programming and concurrent processing.
LLMOps & AI Operations
- Build production-grade LLM deployment pipelines.
- Implement:
- Prompt versioning
- Model versioning
- Experiment tracking
- Deployment automation
- Monitoring
- Governance
- Establish CI/CD pipelines for AI applications.
- Improve reliability, scalability, and operational efficiency.
Agent Evaluation & Observability
- Implement AI monitoring using:
- Evaluate:
- Hallucinations
- Response quality
- Latency
- Token usage
- Agent execution
- Build automated evaluation pipelines and quality dashboards.
- Monitor production AI systems for performance and accuracy.
Cloud AI Platforms
Develop AI solutions using:
- Azure AI Services
- Azure OpenAI
- Azure Machine Learning
- AWS Bedrock
- Amazon SageMaker
- Google Vertex AI
Deploy scalable cloud-native AI services with security and governance best practices.
Database & Data Engineering
- Design AI data pipelines.
- Develop SQL queries and optimize PostgreSQL databases.
- Integrate structured and unstructured enterprise data into AI workflows.
- Manage embeddings, metadata, and AI-related datasets.
DevOps & Engineering
- Maintain code quality using Git-based workflows.
- Build CI/CD pipelines for AI services.
- Containerize applications using Docker.
- Collaborate with DevOps teams for cloud deployment and monitoring.
Required Technical Skills
Programming
- Python (Advanced)
- FastAPI
- REST APIs
- SQL
- PostgreSQL
Generative AI
- Large Language Models (LLMs)
- Prompt Engineering
- Prompt Optimization
- Function Calling
- Tool Calling
- AI Guardrails
- AI Safety
Agentic AI
- LangChain
- LangGraph
- CrewAI
- Autonomous AI Agents
- Multi-Agent Systems
- Agent Memory
- Tool Integration
- Workflow Orchestration
Model Context Protocol
- MCP Architecture
- MCP Servers
- MCP Clients
- Enterprise Tool Integration
Retrieval-Augmented Generation
- RAG
- Semantic Search
- Embeddings
- Hybrid Search
- Document Processing
- Re-ranking
Vector Databases
- Pinecone
- ChromaDB
- Weaviate
- FAISS
LLMOps
- LangSmith
- Langfuse
- Prompt Versioning
- Model Monitoring
- AI Evaluation
- Experiment Tracking
- Observability
Cloud Platforms
- Azure AI Services
- Azure OpenAI
- Azure ML
- AWS Bedrock
- Amazon SageMaker
- Google Vertex AI
- Databricks
DevOps
Preferred Qualifications
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Machine Learning, or a related field.
- Experience deploying enterprise AI applications at scale.
- Hands-on experience with AI governance, security, compliance, and responsible AI frameworks.
- Experience integrating AI solutions with enterprise systems such as ERP, CRM, ITSM, or document management platforms.
- Strong understanding of distributed systems, scalable architectures, and cloud-native application development.
- Excellent problem-solving, communication, and stakeholder management skills.
Nice to Have
- Kubernetes
- MLflow
- Hugging Face
- Ollama
- vLLM
- Ray
- Apache Spark
- Delta Lake
- Apache Airflow
- Knowledge Graphs
- GraphRAG
- Neo4j
- OpenTelemetry
- Terraform