> Markdown version of [/jobs/ext/4654038-principal-software-engineer-it](https://www.wearedevelopers.com/jobs/ext/4654038-principal-software-engineer-it). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Principal Software Engineer - IT

- **Company:** Dell Technologies Inc.
- **Location:** United States
- **Experience:** Expert
- **Contract:** Internship / Graduate position
- **Skills:** LangGraph Framework, JavaScript (Programming Language), Encodings, Continuous Integration, Relational Databases, Cursor, Elasticsearch, Python (Programming Language), PostgreSQL, OAuth, Open Web Application Security, Regression Testing, Software Engineering, Systems Integration, TypeScript, Management of Software Versions, Datadog, Data Logging, GitHub Copilot, Retrieval-Augmented Generation, Large Language Models, Claude Code, Multi-Agent Systems, Indexer, AI Coding Agents, Langfuse — LLM Observability and Analytics Platform, Build Management, Kubernetes, Graphql, Machine Learning Operations, Dynatrace, Docker
- **Published:** November 10, 2026
- **Apply:** https://www.jobmonkeyjobs.com/career/28172771/Principal-Software-Engineer-It-Any-Bangalore-1312

## About the Role

1. 8+ years in software engineering with direct ownership of systems in production; agentic systems personally built and shipped, not prototypes or proofs of concept.
 2. Strong Python plus at least one of TypeScript/JavaScript or Go, with demonstrable testing, review and maintainability practice.
 3. Hands-on experience with LangGraph (or equivalent agent orchestration), embedding concepts and retrieval-augmented generation, and LLM observability tooling such as LangFuse.
 4. Working knowledge of Kubernetes, Docker, PostgreSQL and Elasticsearch, alongside REST/GraphQL APIs, OAuth and scoped credential handling.
 5. Observability and delivery engineering: structured logging, distributed tracing, CI/CD pipelines and automated quality gates.

Desirable Requirements

 1. Experience building MCP servers or agent tooling, or extending AI coding assistants such as Claude Code, GitHub Copilot or Cursor.
 2. LLMOps experience in production (versioning, staged rollout, regression detection) and familiarity with the OWASP Top 10 for LLM Applications.

## Description

1. You will build production-grade agentic workflows that replace manual and duplicated security processes across functional teams.
 2. You will deliver one consolidated implementation per process, engineered for reliability, cost and observability from day one.
 3. You will leave behind reusable components so every workflow after yours starts from existing code.

You will:

 1. Build agentic implementations of security workflows using LangGraph (or an equivalent orchestration framework) - agent loops, sub-agent orchestration, state and checkpoint handling, and deterministic gating and verdict logic.
 2. Implement context strategy in code: retrieval and search, memory, embedding-based grounding against enterprise data sources, prompt assembly and schema-constrained output.
 3. Instrument every workflow for operations using LangFuse (or equivalent) for execution traces, token and cost accounting, and latency measurement, and engineer for cost/latency through caching, model routing and context compaction.
 4. Build and deploy on Kubernetes and Docker, with PostgreSQL for relational data and Elasticsearch for search/retrieval indexing, integrating against REST/GraphQL APIs, event consumers and MCP servers with scoped credentials.
 5. Harden systems against prompt injection and tool abuse, resolve production defects at root cause, and validate delivered workflows with functional owners before release.