How to Apply:

Please submit your application to [email protected]

Job Title: AI Engineer

Location: Bangalore, India

Department: IT

Position Summary:

As PennEngineering accelerates its Speed of Now transformation (respond in 1 hour, quote in 1 day, samples in 1 week, finished product in 1 month), we are building an internal capability to design, develop, and deploy AI-powered workflows, automation, and agentic solutions that improve speed, consistency, and quality across the business.

The AI Engineer is responsible for converting validated business user stories into production-ready AI-powered workflows and AI agents. Some use cases will be addressed through AI-driven workflow automation, while others will require multi-step agentic AI. This role operates as part of a cross-functional delivery model, supported by solution architecture, IS/IT engineering, DevOps, as well as engagement with business stakeholders and subject-matter experts.

Key Responsibility

1. Agentic AI Development
   • Design and build multi-step, multi-tool AI agents using LangGraph, CrewAI, AutoGen, or AWS Bedrock Agents
   • Architect and implement Retrieval-Augmented Generation (RAG) pipelines, tool-use patterns, memory systems, and agent orchestration layers
   • Engineer robust agent behaviors including planning, reflection, error recovery, and human-in-the-loop checkpoints for enterprise-safe operation
   • Design and maintain prompt engineering systems — structured prompts, prompt versioning, few-shot libraries, and evaluation harnesses
   • Implement guardrails, content filtering, output validation, and observability hooks to ensure reliable, auditable agent operation
   • Maintain an internal library of reusable agent components, tool connectors, and workflow templates with version control and telemetry
   • Operate AI-assisted coding tools (Cursor, Claude Code, Amazon Kiro, or similar) as a core part of your development workflow — applying and adapting established team coding workflows to accelerate delivery, maintain quality, and contribute workflow improvements
2. Agile Delivery
   Operate in an iterative agile model:
   • User-story intake and prioritization
   • AI workflow or agent design and build
   • Testing and validation with business SMEs
   • Pilot deployment and data-driven refinement
   • Establish a predictable pipeline and regular release cadence
   • Ensure traceability from user story to AI solution to business outcome
3. Engineering & Integration
   • Integrate AI agents with enterprise platforms including ERP systems, CRM, document management, and
   • structured/unstructured data stores
   • Develop and consume REST and GraphQL APIs; design event-driven integrations using AWS SNS, SQS, or
     EventBridge
   • Connect agents to vector databases (Pinecone, pgvector, OpenSearch) and enterprise knowledge bases for
     grounded, contextual reasoning
   • Work with the IS team to ensure access to clean, governed, structured data where required
   • Collaborate with IS solution architects to align designs with enterprise standards
   • Ensure all AI solutions meet corporate security, compliance, and audit requirements
4. Cloud & Infrastructure
   • Build and deploy AI workloads on AWS using Bedrock, Lambda, ECS/EKS, SageMaker, API Gateway, and S3
   • Implement infrastructure-as-code for AI environments using Terraform or AWS CDK
   • Configure CI/CD pipelines for AI solutions including automated testing, prompt regression checks, and
     blue/green deployments
   • Instrument agents with structured logging, distributed tracing, and metrics dashboards using CloudWatch or
     equivalent

Requirements:

• 3–4 years of overall software engineering experience, with at least 2 years focused on AI/LLM application development and agentic systems
• Production experience building and operating multi-step AI agents using LangChain, LangGraph, CrewAI, AutoGen, AWS Bedrock Agents, or equivalent
• Strong Python engineering skills — well-structured, testable, production-quality code
• Hands-on experience with RAG architectures: chunking strategies, embedding models, vector store selection, retrieval optimization, and re-ranking
• Practical knowledge of prompt engineering at scale: structured prompts, chain-of-thought, few-shot design, and prompt evaluation
• Experience with AWS cloud services in a production context (Lambda, Bedrock, ECS, S3, API Gateway, CloudWatch)
• Working knowledge of CI/CD practices and deploying AI solutions through automated pipelines
• Understanding of AI observability: logging agent reasoning traces, tracking token usage, monitoring for quality drift
• Proficient in the use of AI-assisted coding tools (Cursor, Claude Code, Amazon Kiro, or similar) as a core part of your engineering workflow — with the ability to define, follow, and improve structured coding workflows that leverage these tools effectively
• Strong communication skills — able to translate technical designs into clear explanations for non-technical stakeholders
• Bachelor’s degree in computer science, Engineering, or a related technical field

Preferred Qualifications:

• Experience with AWS Quick Suite or similar enterprise AI platforms
• Experience with structured agent evaluation frameworks and LLM testing methodologies (e.g., LangSmith, RAGAS, or custom harnesses)
• Familiarity with Model Context Protocol (MCP) and emerging standards for tool-use and agent interoperability
• Experience with fine-tuning or adapting open-source models (Llama, Mistral, or similar) for domain-specific tasks
• Knowledge of data engineering, ETL pipelines, and working with enterprise data platforms (Snowflake, Databricks, or similar)
• Experience in manufacturing, supply chain, or industrial environments
• Familiarity with agile methodologies and product development practices
• Experience with multimodal AI applications — document understanding, image analysis, or structured data extraction