Senior AI Engineer – Multi-Agent & LLM Systems

Key Responsibilities

Multi-Agent Systems Architecture

Design and implement multi-agent LLM orchestration frameworks

Architect:

Planner–Executor models

Tool-using agents

Memory-enabled agents

Hierarchical and collaborative agent systems

Define inter-agent communication protocols

Build structured reasoning and orchestration pipelines

Optimize token usage, latency, throughput, and scalability

Ensure resilience, failover handling, and workflow robustness

LLM Systems & RAG Architecture

Design scalable Retrieval-Augmented Generation (RAG) systems

Define:

Embedding strategies

Intelligent chunking frameworks

Retrieval optimization methods

Hybrid search architectures

Implement prompt engineering, fine-tuning, and instruction tuning strategies

Design hallucination mitigation and groundedness systems

Establish prompt versioning and governance standards

Optimize inference cost and model performance

LLM Evaluation & Reliability Engineering

Design evaluation frameworks for:

Hallucination detection

Faithfulness assessment

Response quality benchmarking

Groundedness scoring

Implement automated LLM evaluation pipelines

Build synthetic dataset generation systems

Design human-in-the-loop evaluation workflows

Monitor model drift and agent failures

Develop observability dashboards and reliability monitoring systems

Define enterprise AI governance standards

Machine Learning & Predictive Systems

Lead development of:

Classification and regression models

Deep learning architectures

Anomaly detection systems

Knowledge graph reasoning engines

Establish experimentation and statistical validation frameworks

Optimize model performance and deployment strategies

Production AI & Infrastructure

Architect enterprise-grade AI deployment infrastructure

Define and manage:

MLOps pipelines

LLMOps workflows

Monitoring & observability systems

Deploy AI systems using:

AWS / GCP / Azure

Docker / Kubernetes

CI/CD pipelines

Ensure scalability, reliability, and cost optimization for high-volume AI workloads

Technical Leadership & Strategy

Serve as architectural authority for AI systems

Mentor AI engineers, ML engineers, and data scientists

Conduct architecture reviews and technical evaluations

Translate business challenges into scalable AI frameworks

Collaborate with leadership on AI innovation and strategic roadmap planning

Required Qualifications

Master’s or PhD in:

Artificial Intelligence

Machine Learning

Computer Science

Related Technical Field

6+ years of experience in AI/ML Engineering

Minimum 3 years leading complex AI initiatives

Strong proficiency in Python

Proven experience deploying AI systems into production environments

Required Technical Skills

AI/ML Expertise

Machine Learning Algorithms

Deep Learning Architectures

Transformer Models

Statistical Modeling

Reinforcement Learning Concepts

AI Evaluation Systems

Multi-Agent & LLM Systems

LangGraph (Mandatory)

LangChain

Multi-Agent Orchestration

Agent Workflows & Memory Systems

Prompt Engineering & Fine-Tuning

RAG System Design

Infrastructure & Deployment

AWS / GCP / Azure

Docker & Kubernetes

CI/CD Pipelines

Monitoring & Observability Tools

Distributed Systems Architecture

Databases & AI Systems

Vector Databases:

Pinecone

Weaviate

Similar Platforms

Knowledge Graph Systems

Search & Retrieval Architectures

Preferred Qualifications

Experience building production-grade multi-agent AI systems

Experience scaling enterprise AI platforms

Exposure to Speech AI systems (STT/TTS)

Knowledge graph reasoning expertise

Experience in enterprise AI governance and reliability engineering

What We’re Looking For

Strong systems-level architectural mindset

Research-oriented thinking with production pragmatism

Excellent analytical and problem-solving abilities

Strong mathematical and statistical foundation

High ownership and execution mindset

Excellent communication and stakeholder management skills

Success Metrics

Successful deployment of multi-agent AI systems in production

Reduced hallucination rates and improved AI reliability

Scalable and cost-efficient AI infrastructure

Institutionalized LLM evaluation frameworks

Measurable business impact from AI initiatives

Work Environment

High-impact AI innovation environment

Opportunity to work on enterprise-scale AI systems

Collaborative engineering and research culture

Fast-paced and technically challenging projects