Engineer, Principal
Qualcomm · Bengaluru · onsite · Posted 28d ago
Undisclosed10–15 yrsfulltimeSourced from
About a minute. You'll make an account on the way through.
About this role
Company: Qualcomm India Private Limited
Job Area: Engineering Group, Engineering Group > Software Engineering
Job Summary Agentic Software Development Engineer - Agentic Platform and Enterprise Workflow Automation
About the Role
As a Agentic Software Development Engineer, you will lead the design and delivery of enterprise-grade agentic AI systems that bring autonomous multi-step reasoning to complex, tool-heavy workflows. You will work at the intersection of AI engineering and deep domain expertise partnering closely with subject matter experts to decompose workflows, define knowledge schemas, and deliver agents that are reliable enough for production use by engineers who depend on them daily.
This is a hands-on technical leadership role. You will define the standards that let teams scale in parallel, own the architecture end-to-end, and be the person other engineers come to when the problem is hard.
Key Responsibilities Agent Architecture and Platform Onboarding - Design and implement LangGraph-based agent graphs for multi-step, tool-heavy workflows; own the decomposition of existing automation scripts and workflow descriptions into structured agent phases, HITL gates, and MCP tool interfaces
- Build and maintain MCP (Model Context Protocol) tool wrappers that connect agents to enterprise data sources and domain-specific tooling; own retry logic, auth integration, format-version handling, and failure modes
- Define design pattern archetypes that cover the majority of workflow types, enabling engineering pairs to agentize independently and in parallel using a shared playbook
- Design ontology schemas (OWL/RDF or equivalent) that capture domain-specific facts signals, decisions, constraints, and validated outcomes to ground LLM reasoning in verified knowledge rather than inference
- Build and maintain RAG pipelines and vector stores over domain documentation; own ingest, chunking strategy, embedding model selection, retrieval quality evaluation, and refresh automation
- Drive the strategy for what facts belong in a structured ontology versus a RAG index versus a prompt
- Build evaluation frameworks for non-deterministic agent outputs: golden dataset curation process, semantic correctness scoring, CI triggers on agent code changes, and regression gates on LLM model version updates
- Own the quality bar: define what correct means for each agent, build the harness that measures it, and establish the process for expanding coverage as agents reach production
- Lead the discovery phase: pair with domain experts to understand complex workflows end-to-end before any code is written; produce skill/task maps, EDA tool interaction catalogs, and archetype classifications that unblock parallel engineering work
- Define and enforce standards: agent scaffold templates, ontology schema templates, dummy stage patterns, and co-design SOPs that let HW+SW pairs work independently without reinventing structure
- Mentor engineers; review agent designs; drive architecture decisions for the agentic layer
- 10+ years in software engineering with at least 3 years focused on AI/ML systems in production
- Demonstrated experience building agentic or multi-step LLM systems beyond demo/prototype scale: agents that run in production, handle failures gracefully, and are tested against real domain inputs
- Experience working in a co-design model with non-engineering domain experts (scientists, analysts, domain specialists) you can translate between domain knowledge and software architecture
- Python (strong): async, type annotations, production-quality code
- LangGraph or equivalent graph-based agent framework; experience with LangChain or LlamaIndex
- MCP (Model Context Protocol) or equivalent tool-serving pattern
- Vector databases: Chroma, Milvus, pgvector, or similar; experience with embedding pipelines
- Knowledge graphs or ontologies: OWL/RDF, SPARQL, or equivalent structured knowledge systems
- CI/CD for AI systems: pytest, golden dataset frameworks, regression on non-deterministic outputs
- Experience with workflow orchestration engines (Temporal, Airflow, or equivalent durable execution platforms)
- Familiarity with enterprise API integration patterns: OAuth, rate limiting, retry strategies, auth token management
- Experience building evaluation frameworks for LLM outputs, including domain-expert-in-the-loop curation processes
- Fine-tuning experience on domain-specific data
- Bachelor's in Computer Science or Engineering required
- Master's with ML or Systems specialization preferred
- Bachelor's degree in Engineering, Information Systems, Computer Science, or related field and 8+ years of Software Engineering or related work experience.
- Master's degree in Engineering, Information Systems, Computer Science, or related field and 7+ years of Software Engineering or related work experience.
- PhD in Engineering, Information Systems, Computer Science, or related field and 6+ years of Software Engineering or related work experience.
- 4+ years of work experience with programming languages such as C, C++, Java, Python, etc.
Sourced from naukri
Skills
AutomationDesign PatternRetrieval Augmented Generationontologyorchestrationprogramming languagePrototypepytestapache airflowProgrammingOAuthRAG PipelinesKnowledge GraphsLarge Language Models (LLMs)Event DrivenPythonOnboardingJavaArchitectureAPI IntegrationLangchainArtificial IntelligenceMachine Learning
About Qualcomm
Qualcomm
Semiconductors
22k+
employees
1996
30 years old
San Diego,California
United States
About
Qualcomm invents breakthrough technologies that transform how the world connects, computes and communicates.
Industries
SemiconductorsHardware & Networking
Employee ratings
1,207 reviews
3.7/ 5
Culture
3.4
Career growth
3.2
Work-life
3.3
Employees rate it well for
Work Life Balance267Salary160Work Culture155Learning100Senior Management91
Find them on