Data Scientist

Key Responsibilities

• Design, fine-tune, and manage

  prompts

  for diverse enterprise LLM use cases.
• Operate, monitor, and troubleshoot

  agentic AI applications

  , diagnosing whether issues stem from:
• Prompt structure/quality
  
• Model configuration or performance
  
• Tool usage, API failures, or memory/recall issues
  
• Build

  diagnostic playbooks

  for LLM-driven failures, including fallback strategies, retries, and re-routing to human workflows.
• Collaborate with

  AI architects, ML engineers, and DevOps

  teams to optimize agent orchestration across platforms such as

  LangGraph, CrewAI, AutoGen, etc.

• Support integration of agentic systems with enterprise tools (Jira, ServiceNow, Glean, Confluence) via

  REST APIs, webhooks, and adapters

  .
• Implement

  observability and logging best practices

  for model outputs, latency, and agent performance metrics.
• Contribute to building

  self-healing mechanisms and alerting strategies

  for production AI workflows.

Required Qualifications

• 36 years

  of experience in

  Software Engineering, DevOps, or ML Ops

  , with exposure to AI/LLM workflows.
• Strong foundation in

  prompt engineering

  and experience with

  LLMs (GPT, Claude, LLaMA, etc.)

  .
• Practical understanding of

  AIOps platforms

  or operational AI use cases (incident triage, log summarization, RCA, etc.).
• Exposure to

  agentic AI architectures

  : LangGraph, AutoGen, CrewAI, or similar.
• Proficiency in

  Python scripting

  , RESTful APIs, and basic system debugging.
• Strong

  analytical and problem-solving

  skills to trace issues across multi-step pipelines and asynchronous agents.