Must Have Technical/Functional Skills:
10+ years of software engineering experience, with 4+ years in AI/ML or LLM-based systems
Python (FastAPI, Pydantic, boto3) and TypeScript (React, Node.js)
Strong AI/ML experience — LLM APIs, prompt engineering, RAG architectures, embeddings, vector search
Experience building AI pipelines — model orchestration, token management, confidence scoring, intelligence buildouts
AWS fundamentals — ECS/Fargate, Lambda, DynamoDB, IAM, CloudWatch, EventBridge
CI/CD pipeline experience — GitLab CI (or similar), environment management
Experience mentoring or leading offshore engineers
Strong verbal and written communication Nice to Have
Experience building internal engineering platforms or cognitive/AI platforms
Dynatrace or similar APM (DQL queries, alerting, SLOs)
Terraform for infrastructure-as-code
Security engineering — SAST/DAST, container scanning, IAM policy design
Financial services / regulated environment experience
Claude Code, GitHub Copilot, or AI-assisted development workflows
Event-driven architectures (EventBridge, SQS, SNS)
Production on-call sre experience Tech Stack Python | FastAPI | React | TypeScript | Tailwind CSS
| AWS (ECS, Lambda, DynamoDB, S3, EventBridge, IAM) | Terraform | GitLab CI | Docker | Dynatrace
| Jira/Confluence APIs | ServiceNow | Ally AI Gateway (GPT/Claude) | RAG/Embeddings | Vector Search
| Claude Code/Codex/Gemini/DeepSeek |
Roles & Responsibilities:
AI & Cognitive Engineering (70%)
Build and extend internal platform features
Python backend (FastAPI) and React frontend
Develop AI automation
LLM integrations, prompt engineering, self-heal pipelines, knowledge retrieval
Lead technical design for new cognitive capabilities COG scoring, DELTA analytics, proactive monitoring
Build observability for AI systems token budgets, model accuracy, drift detection, confidence scoring.
Design and implement RAG pipelines embeddings, vector search, knowledge ingestion, semantic retrieval
Contribute to Guild Commons skills, agents, hooks shared across the organization
Drive adoption of AI tooling (Claude Code) across the team; support Tier 1/Tier 2 enablement
Pioneer self-heal automation detection, decision, approval, and remediation pipelines
Mentor offshore engineers on AI patterns, prompt engineering, and architectural decisions
DevSecOps & Infrastructure (15%) - Support CI/CD pipelines — troubleshoot build failures, optimize stages, manage environment promotions
Manage AWS infrastructure as needed — ECS services, Lambda functions, DynamoDB, IAM
Support production incident response during US business hours when on rotation
Maintain Terraform configurations; review infrastructure changes
Release Management & Quality (15%)
Support releases across environments (CIT → UAT → CAP → PSP → PROD)
Contribute to quality gates — automated testing, coverage enforcement, static analysis
Support ServiceNow change records and Jira workflows as needed - Generate release metrics
DORA calculations, deplo yment outcomes
Salary: $75,000 - $130,000
More Information
Application Details
- Organization DetailsTCS / Tata Consultancy Services
Recommended Comments
There are no comments to display.
Join the conversation
You are posting as a guest. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.