Staff Software Engineer

Responsibilities:

• Hands-on development of AI-powered applications using Python, conducting code reviews and continuously improving application quality, scalability, and reliability.
• Performs advanced development, support, and implementation of enterprise AI solutions using specialized business and domain expertise.
• Partners with architects to translate enterprise AI and GenAI strategies into detailed solution designs and implementation plans.
• Leads large AI and machine learning initiatives with limited or no oversight.
• Evaluates AI, machine learning, and generative AI industry trends and recommends technologies and approaches that improve business outcomes.
• Proposes and champions innovative AI solutions, architectures, and engineering practices that enhance operational efficiency and customer experience.
• Sets standards to deliver high-quality AI products and services while maintaining responsible AI principles, governance, and security.
• AI Engineering: Designs and develops enterprise AI applications using Python, leveraging Large Language Models (LLMs), prompt engineering, and AI orchestration frameworks.
• AI Engineering: Designs and implements Retrieval-Augmented Generation (RAG) architectures, embedding pipelines, semantic search solutions, and enterprise knowledge retrieval platforms.
• AI Engineering: Builds production-grade AI agents using LangChain, LangGraph, ADK, or similar frameworks, including tool calling, memory management, orchestration, and human-in-the-loop workflows.
• Data & AI: Designs and implements vector search solutions using Azure AI Search, Vertex AI Vector Search, Pinecone, Weaviate, pgVector, or similar vector databases.
• Cloud AI: Deploys and manages machine learning and GenAI workloads using Vertex AI or Azure Machine Learning platforms, including training, inference, monitoring, and model lifecycle management.
• AI Integration: Designs and implements AI-driven integrations with enterprise platforms using REST APIs, Kafka, Apache Camel, event-driven architectures, and microservices.
• Computer Vision and Multimodal AI: Develops solutions involving image, video, OCR, document intelligence, and multimodal AI capabilities for business use cases.
• AI Governance: Implements responsible AI controls, model evaluation, tracing, observability, prompt security, guardrails, and performance monitoring.
• Quality Engineering: Defines testing and validation strategies for AI applications, including model evaluation, prompt testing, integration testing, and automated testing frameworks.
• Performance Engineering: Monitors and optimizes AI applications for response quality, latency, throughput, scalability, model cost, and resource utilization.
• Production Operations: Ensures AI services run reliably in production environments using an SRE mindset, including observability, monitoring, tracing, incident management, and operational readiness.
• Mentors engineers on AI, ML, GenAI, cloud AI platforms, architecture patterns, and engineering best practices.

Requirements:

• Skills Required: Python, AI/ML, Vertex AI, Azure ML, LangChain, RAG, Vector Databases.
• Experience Range: 9 - 12 years.
• 9+ years of software engineering experience developing enterprise applications.
• 4+ years of experience leading engineering teams and delivering large-scale technology initiatives.
• 5+ years of programming experience using Python and developing enterprise-grade applications.
• 3+ years of experience designing and implementing AI/ML or generative AI solutions.
• Hands-on experience with Large Language Models (LLMs), prompt engineering, and AI-powered application development.
• Experience designing and implementing Retrieval-Augmented Generation (RAG) solutions.
• Experience working with vector databases and semantic search technologies.
• Experience deploying AI/ML models using Vertex AI or Azure Machine Learning platforms.
• Experience developing cloud-native applications on Azure or GCP.
• Experience developing REST APIs, microservices, and event-driven architectures.
• Experience integrating enterprise systems using Kafka, Apache Camel, APIs, and messaging technologies.
• Experience implementing MLOps, CI/CD pipelines, model deployment, monitoring, and governance processes.
• Broad expertise with software development lifecycle methodologies, including Agile practices.
• Experience analyzing and optimizing AI application performance, scalability, and operational cost.
• Experience implementing enterprise-grade security, compliance, and responsible AI practices.