AI/ML Engineer

Position Overview

We are seeking an experienced AI/ML Engineer to design and implement intelligent systems using large language models (LLMs) for observability and operational workflows. This role focuses on building AI-driven solutions for anomaly detection, alert triage, and automated root cause analysis in production environments.

Key ResponsibilitiesLLM Development & Deployment

• Design and deploy large language model solutions using Ollama, AWS Bedrock, or similar platforms
• Implement agentic networks and multi-agent systems for complex operational workflows
• Develop context-based prompt engineering strategies for production LLM applications
• Fine-tune and optimize LLMs using LoRA (Low-Rank Adaptation) techniques
• Integrate Model Context Protocol (MCP) for enhanced agent communication

Observability & Operations

• Build AI-driven observability workflows for monitoring and operational intelligence
• Design and implement intelligent alerting systems that reduce noise and improve signal quality
• Develop automated alert triage mechanisms using ML-based classification
• Create root cause analysis systems that leverage LLMs for faster incident resolution
• Integrate LLM capabilities into existing operational pipelines and monitoring infrastructure

System Integration & Optimization

• Develop robust APIs and integrations for LLM-powered features
• Optimize model performance for latency-sensitive operational use cases
• Implement monitoring and evaluation frameworks for LLM outputs
• Build feedback loops to continuously improve model accuracy and relevance

Required QualificationsTechnical Skills

• Programming: Strong proficiency in Python with experience in production-grade code
• ML Frameworks: Hands-on experience with PyTorch, TensorFlow, LangChain, or similar frameworks
• LLM Deployment: Practical experience deploying LLMs using platforms like:
• Ollama for local/edge deployment
• AWS Bedrock for cloud-based solutions
• OpenAI API, Anthropic Claude API, or similar
• Prompt Engineering: Proven ability to design effective prompts and context strategies
• Version Control: Git/GitHub proficiency

AI/ML Experience

• 3+ years of experience in machine learning or AI engineering
• Demonstrated experience working with large language models in production
• Understanding of transformer architectures and attention mechanisms
• Experience with model evaluation, testing, and performance optimization
• Familiarity with vector databases and semantic search (Pinecone, Weaviate, ChromaDB, etc.)

System Architecture

• Experience building scalable ML systems and APIs
• Understanding of microservices architecture and containerization (Docker, Kubernetes)
• Familiarity with cloud platforms (AWS, GCP, or Azure)
• Knowledge of CI/CD pipelines for ML models

Preferred QualificationsAdvanced ML Skills

• Experience with LoRA (Low-Rank Adaptation) or other parameter-efficient fine-tuning methods
• Knowledge of retrieval-augmented generation (RAG) architectures
• Experience with multi-agent systems and agentic frameworks
• Understanding of Model Context Protocol (MCP) for agent orchestration
• Experience with reinforcement learning from human feedback (RLHF)

Domain Expertise

• Background in observability, monitoring, or DevOps/SRE
• Experience with anomaly detection algorithms and time-series analysis
• Knowledge of alert management systems and incident response workflows
• Familiarity with APM tools (Datadog, New Relic, Grafana, Prometheus, etc.)
• Understanding of distributed systems and microservices architectures

Additional Skills

• Experience with real-time data processing and streaming systems
• Knowledge of statistical methods for outlier detection
• Familiarity with explainable AI (XAI) techniques
• Experience with A/B testing and experimentation frameworks
• Publications or contributions to open-source ML projects

Educational Background

• Bachelor's or Master's degree in Computer Science, Data Science, Machine Learning, or related field
• Equivalent practical experience will be considered
• PhD in AI/ML or related field is a plus

What You'll Work OnNear-Term Projects

• Deploy LLM-powered alert triage system to reduce on-call burden
• Build intelligent incident summarization using context-aware prompts
• Implement anomaly detection for production metrics using ML models
• Create automated root cause analysis workflows

Long-Term Vision

• Develop self-healing systems that use LLMs for autonomous remediation
• Build predictive models for proactive issue detection
• Create natural language interfaces for operational queries
• Design multi-agent systems for complex operational decision-making

Job Type: Full-time

Pay: ₹2,500, ₹9,500,000.00 per year

Benefits:

• Food provided
• Health insurance
• Life insurance
• Paid sick time
• Paid time off