Description

Key Responsibilities

AI/ML Model Development

• Design and implement ML models for anomaly detection, predictive failure analysis, and connector health monitoring.
• Build and deploy supervised and unsupervised learning pipelines for IT operations analytics and AIOps use cases.
• Develop time-series forecasting models to anticipate connector degradation and L4 incident spikes.
• Implement model versioning, A/B testing, automated retraining, and drift monitoring pipelines.
• Maintain feature stores, data quality standards, and model registries aligned with MLOps best practices. LLM & Generative AI Integration
• Integrate LLM APIs such as AWS Bedrock, OpenAI, and Anthropic Claude into Concierto connector orchestration workflows.
• Build RAG pipelines for intelligent connector documentation search, incident summarization, and self-healing runbooks.
• Design and optimize prompt engineering strategies for root cause analysis, change advisory drafting, and test case generation.
• Develop AI agents using LangChain, CrewAI, AutoGen, or equivalent frameworks for autonomous incident triage and connector lifecycle management.
• Deploy and manage LLM inference endpoints on AWS Lambda, ECS, or SageMaker with IAM-secured access controls.

NLP & Intelligent Log Analytics

• Develop NLP-based log parsing, event correlation, and semantic classification modules to accelerate L4 support triage.
• Build natural language query interfaces for operations teams to interrogate connector telemetry and CloudWatch logs.
• Apply NER, intent classification, and text summarization to convert raw incident data into actionable insights.
• Implement vector search and semantic similarity using AWS OpenSearch, Pinecone, or equivalent solutions.

AI-Powered Automation Engineering

• Design agentic AI pipelines that autonomously diagnose, escalate, or resolve common Concierto connector issues.
• Build AI-augmented test automation frameworks that generate, execute, and evaluate test cases for connector APIs.
• Develop self-healing test scripts using pattern recognition and element-level ML locators.
• Integrate AI-based defect prediction and test coverage analysis into CI/CD pipelines.
• Automate connector deployment health checks, rollback triggers, and post-deployment validation using AI-driven observability.

AWS Cloud AI Integration

• Leverage AWS AI/ML services including SageMaker, Bedrock, Comprehend, Forecast, and OpenSearch.
• Integrate AI inference outputs with Java-based connector REST APIs through well-defined, versioned service contracts.
• Optimize ML model latency and throughput for real-time connector event classification and response at scale.
• Apply AWS security best practices including IAM, KMS, and VPC across AI data pipelines and inference endpoints.
• Design feature engineering pipelines from structured and semi-structured AWS event streams and connector logs.

Platform Observability & Intelligent Reporting

• Build AI-powered dashboards and alerts for Concierto connector KPIs using CloudWatch, Grafana, or equivalent tools.
• Generate AI-authored incident summaries, root cause analysis reports, and resolution recommendations.
• Develop executive-ready AI-generated performance narratives and weekly connector health digests.

Collaboration, Agile & Mentorship

• Work cross-functionally with Java, QA, DevOps, and Product Management teams to align AI modules with the Concierto Agentic roadmap.
• Participate in agile ceremonies including sprint planning, backlog grooming, retrospectives, and release planning.
• Maintain model cards, prompt libraries, API integration guides, and AI runbooks as living documentation assets.
• Mentor team members on AI/ML integration patterns, prompt engineering practices, and responsible AI principles.

Required Qualifications

Education & Experience

• Bachelor's or Master's degree in Computer Science, Data Science, AI/ML, Software Engineering, or equivalent.
• 4 to 7 years of hands-on experience in ML engineering, AI application development, or data science roles.
• Minimum 2 years of demonstrated experience integrating AI/LLM/NLP capabilities in production environments.
• Prior experience delivering cloud-native AI solutions on AWS. AI/ML & Data Science Skills
• Proficient in Python with ML frameworks such as scikit-learn, TensorFlow, PyTorch, or equivalent.
• Strong understanding of supervised and unsupervised learning, time-series forecasting, classification, and clustering.
• Hands-on experience with AWS SageMaker for model training, hosting, monitoring, and MLOps pipelines.
• Familiarity with MLflow, Kubeflow, or equivalent MLOps tooling.
• Proficient in feature engineering, data wrangling, and working with structured and unstructured data at scale. LLM, GenAI & NLP Skills
• Hands-on experience with LLM APIs such as OpenAI, AWS Bedrock, Anthropic, or Hugging Face.
• Practical knowledge of RAG architecture, vector databases, and embedding pipelines.
• Proficient in prompt engineering including zero-shot, few-shot, chain-of-thought, and tool-use patterns.
• Experience building NLP pipelines including tokenization, NER, intent classification, summarization, and sentiment analysis.
• Familiarity with agentic frameworks such as LangChain, CrewAI, AutoGen, or equivalent.

Software Engineering & AWS Integration

• Proficient in Python and/or Java with experience exposing and consuming REST APIs in microservices architectures.
• Hands-on experience with AWS services including Lambda, S3, SQS, SNS, CloudWatch, ECS, and IAM.
• Familiarity with CI/CD pipelines using Jenkins, GitHub Actions, or GitLab CI.
• Working knowledge of Docker, Kubernetes, or serverless deployment patterns for AI workloads.
• Proficient in SQL; experience with data lakes, streaming data, or event-driven architectures is an added advantage

Key Skills

Education

Bachelor's degree