Expert Ai Ml Engineer

Tata Consultancy Services; Pennington (NJ); On-site; USD 120,000 - 150,000; Full time

Job summary

RAG Technologies is seeking experts to design and implement enterprise-scale GenAI applications using OpenAI, Claude, Gemini, Llama, and other models. You will build production-grade RAG architectures with vector search and semantic retrieval, and develop AI-powered apps with prompt engineering and memory management.

You will also optimize LLM performance, design hybrid AI architectures, and implement guardrails and compliance frameworks across banking and enterprise data environments.

Qualifications

• Experience designing enterprise-scale GenAI applications.
• Experience with vector search and semantic retrieval.
• Experience with prompt engineering and memory management.
• Experience with production-grade AI pipelines.
• Familiarity with guardrails and compliance frameworks.

Responsibilities

• Design and implement enterprise-scale GenAI applications.
• Build production-grade RAG architectures with vector search and semantic retrieval.
• Develop AI-powered applications using prompt engineering, contextual retrieval, tool calling, and memory management.
• Optimize LLM performance, latency, throughput, hallucination reduction, and response accuracy.
• Design hybrid AI architectures combining structured data, unstructured documents, APIs, and enterprise knowledge sources.
• Implement guardrails, responsible AI controls, content filtering, and compliance frameworks.

Skills

Azure

AWS

GCP

Prompt engineering

Memory management

LLM performance optimization

Hybrid AI architectures

Guardrails & compliance

Tools

LangGraph

CrewAI

AutoGen

Semantic Kernel

MCP (Model Context Protocol)

Kafka

Spark

Databricks

Airflow

Hadoop Ecosystem

Delta Lake

Job description

RAG Technologies-Vector Embeddings,Semantic Search,Hybrid Search,Knowledge Graph RAG,Agentic RAG

Must have experience in one or more: Azure,AWS,GCP

• Design and implement enterprise-scale GenAI applications using OpenAI, Claude, Gemini, Llama, Mistral, and other foundation models.
• Build production-grade RAG architectures with vector search and semantic retrieval.
• Develop AI-powered applications using prompt engineering, contextual retrieval, tool calling, and memory management.
• Optimize LLM performance, latency, throughput, hallucination reduction, and response accuracy.
• Design hybrid AI architectures combining structured data, unstructured documents, APIs, and enterprise knowledge sources.
• Implement guardrails, responsible AI controls, content filtering, and compliance frameworks.

Agentic AI & Multi-Agent Systems

• Build intelligent autonomous and semi-autonomous agentic systems.
• Develop agent workflows using: LangGraph,CrewAI,AutoGen,Semantic Kernel,MCP (Model Context Protocol),Agent-to-Agent Architectures
• Implement: Planning Agents,Task Decomposition Agents,Reflection Agents,Tool Use Agents,Multi-Agent Collaboration Frameworks
• Develop dynamic orchestration frameworks for enterprise workflows.
• Build human-in-the-loop validation and approval mechanisms.

Retrieval Augmented Generation (RAG)

• Build advanced RAG pipelines for banking use cases.
• Implement: Hybrid Search,Semantic Search,Metadata Filtering,Re-ranking Models,Knowledge Graph RAG,Agentic RAG
• Optimize chunking, embeddings, retrieval accuracy, and respons e grounding.
• Build supervised and unsupervised machine learning solutions.
• Fine-tune foundation models and open-source LLMs.
• Develop model evaluation and benchmarking frameworks.
• Design scalable data platforms supporting AI workloads.
• Work with: Kafka,Spark,Databricks,Airflow,Hadoop Ecosystem,Delta Lake
• Develop enterprise metadata and lineage solutions.
• Handle large-scale structured and unstructured data processing.
• Build CI/CD pipelines for AI applications.
• Enable production deployment through Kubernetes and containerized environments.
• Develop observability dashboards and operational runbooks.

Banking Domain Responsibilities

• Build AI use cases supporting: Capital Markets,Investment Banking,Trading Operations,Risk Management,Treasury,Compliance,AML/KYC,Regulatory Reporting
• Apply AI governance standards for regulated financial environments.
• Ensure solutions meet banking security, audit, privacy, and compliance requirements.