The Python AI/ML Developer will design, build, and operate enterprise-grade AI capabilities across Business Applications. This role combines AI agent development, RAG-based knowledge systems, workflow automation, and secure enterprise integrations to deliver scalable solutions across Sales, Support, Customer Success, Marketing, Finance, and Operations.
The ideal candidate brings hands-on experience with Python, LLMs, RAG pipelines, vector databases, APIs, and cloud-native services. They will work closely with enterprise architects, integration engineers, security, data teams, and business SMEs to convert high-value business use cases into reliable production AI solutions.
Key Responsibilities:
Design, develop, and deploy AI agents, copilots, and workflow automations using LLM platforms such as Microsoft Copilot, Anthropic Claude, Workato, or similar technologies.
Build end-to-end RAG solutions, including document ingestion, chunking, embedding, vector indexing, retrieval, ranking, context assembly, and response generation.
Develop reusable AI components, agent templates, orchestration patterns, and integration frameworks to accelerate delivery across business functions.
Integrate AI agents and RAG services with enterprise platforms including Salesforce, Workato, knowledge bases, APIs, data lakes, and other business applications.
Build real-time and batch data pipelines for structured and unstructured data sources.
Implement multi-step agent workflows, tool usage, human-in-the-loop approvals, and controlled write-back patterns.
Optimize retrieval relevance, latency, response quality, prompt performance, and agent reliability.
Define and implement evaluation frameworks for AI quality, including retrieval accuracy, groundedness, hallucination rate, task completion, and user feedback.
Enforce enterprise data-access controls, permissions, masking, auditability, and compliance requirements across AI workflows.
Develop cloud-native services and APIs using Python, microservices, containers, and scalable deployment patterns.
Establish logging, monitoring, tracing, and AI observability for LLM calls, agent behavior, retrieval performance, workflow execution, and production incidents.
Partner with business SMEs to define use cases, success criteria, test scenarios, and measurable business outcomes.
Support production deployment, incident resolution, continuous improvement, and platform standardization.
Required Qualifications:
8 years of experience in software engineering, AI/ML engineering, backend development, or a related technical discipline.
Strong Python development skills, including API development, data processing, and service-oriented architecture.
Hands-on experience building solutions using LLMs, prompt engineering, RAG, agents, or workflow orchestration.
Experience with vector databases, embedding models, semantic search, and retrieval optimization.
Strong understanding of REST APIs, authentication patterns, enterprise integrations, and system design.
Experience integrating with SaaS platforms, business systems, knowledge repositories, or data platforms.
Experience with at least one major cloud platform: Azure, AWS, or Google Cloud Platform.
Familiarity with Docker, Kubernetes, CI/CD pipelines, and cloud-native deployment practices.
Working knowledge of logging, monitoring, tracing, and AI observability tools and practices.
Ability to work across technical and business stakeholders to translate use cases into production-ready solutions.
Preferred Qualifications
Experience with Microsoft Copilot Studio, Anthropic Claude, OpenAI APIs, Workato, LangChain, LlamaIndex, or similar AI and orchestration platforms.
Experience with Salesforce, Service Cloud, knowledge management platforms, CRM data, or customer-support workflows.
Familiarity with MCP, agentic workflows, tool calling, and enterprise AI governance patterns.
Experience implementing role-based access controls, data masking, audit logging, and human approval workflows.
Experience with evaluation frameworks for LLM applications and production model monitoring.
Exposure to event-driven architecture, message queues, and enterprise automation platforms.
Success Metrics:
Number and quality of production AI agents, copilots, and RAG solutions deployed.
Measurable business impact, including productivity improvement, case deflection, cycle-time reduction, and automation coverage.
Retrieval accuracy, response quality, groundedness, and reduction in hallucinations.
Reliability, latency, scalability, and operational health of deployed AI services.
Reuse of common components, integrations, and agent frameworks across business functions.
Adoption and satisfaction among business users and operational teams.
Compliance with security, governance, auditability, and data-access requirements.
Never miss an opportunity! Create an alert based on the job you applied for.
