Apex IT
Senior Consultant – AI Application Engineer
УдалённоIndia только
- Роль
- AI / ML
- Опыт
- Синьор
Зарплата не указана
Проверьте доступность
Доступно для: IN only. Укажите, откуда вы работаете, чтобы проверить доступность.
Коротко по делу
Senior AI application engineer for building production GenAI/LLM apps, RAG systems, orchestration workflows, and reusable accelerators. Must have strong software engineering, Python and/or Node.js, LLM APIs, vector databases, prompt engineering, cloud architecture, and secure integrations. Role is Bangalore/India remote.
Ключевые навыки
RAGPrompt engineeringLLM applications
Обязательные навыки
AI/LLM-powered applicationsAPIsOpenAI/Azure OpenAI/Anthropic/GooglePython/Node.jsVector databasesEmbeddingsLangChain/LlamaIndex/Semantic KernelCloud architectureAI application debugging
Желательные навыки
SalesforceOracleMicrosoftAgentic workflowsObservability/evaluation platforms
Apex IT is a global consulting firm that provides award-winning services to transform the customer, employee, and student experiences. Since 1997, Apex IT our Salesforce and Oracle experts have provided a full range of enterprise solutions including CRM and related applications that support sales, marketing, and service; financial reporting; HR; and Business Intelligence. As a remote company, we have top talent all over the United States and India and are continuously growing. We provide our team with a flexible work-life balance in addition to the traditional benefits.
Job Title: Senior Consultant – AI Application Engineer
Work Location/Travel: Bangalore/Remote
Role Summary
The Senior AI Application Engineer will design and build reusable AI-powered applications and accelerators that support internal operations, consulting delivery, and client-facing innovation. This role will be responsible for translating business and product requirements into scalable technical solutions using commercial language models, orchestration frameworks, retrieval systems, and enterprise integrations.
Key Duties and Responsibilities
1. AI Solution Architecture
- Design end-to-end AI application architecture for internal and client-facing use cases
- Define patterns for prompt orchestration, agent workflows, retrieval-augmented generation (RAG), tool calling, and enterprise integrations
- Select appropriate models, frameworks, vector stores, and deployment patterns based on cost, performance, and security considerations
- Establish reusable design patterns for future AI accelerators and company-owned IP
2. Product and Feature Development
- Build production-grade AI applications, copilots, assistants, and workflow automations
- Lead development of reusable AI components that can be scaled across multiple engagements
- Translate roadmap initiatives into technical implementation plans, milestones, and deliverables
- Partner with product and business stakeholders to refine use cases into buildable solutions
3. LLM and GenAI Engineering
- Evaluate and implement commercial LLMs through APIs and enterprise tooling
- Develop robust prompt strategies, context handling logic, tool usage patterns, and fallback mechanisms
- Design and optimize RAG pipelines using structured and unstructured enterprise knowledge sources
- Improve output quality, reliability, and usability of AI applications through testing and iteration
4. Engineering Standards and Production Readiness
- Define coding standards, deployment standards, logging, monitoring, guardrails, and evaluation practices for AI applications
- Implement mechanisms for observability, tracing, prompt versioning, and response quality review
- Ensure solutions are secure, maintainable, scalable, and aligned with enterprise architecture principles
- Guide non-functional requirements including latency, reliability, token usage, and cost optimization
5. Technical Leadership
- Serve as the technical lead for AI engineering efforts
- Mentor and guide the AI Developer / GenAI Engineer
- Support technical decision-making, effort estimation, and feasibility assessments
- Collaborate with cross-functional teams including product, architecture, delivery, QA, and operations
6. Stakeholder Collaboration
- Participate in discovery sessions with business and delivery teams to identify opportunities for AI enablement
- Work with consulting, sales, and solution engineering teams to understand repeatable use cases
- Support demos, pilots, proofs of concept, and internal enablement where required
7. Evaluation and Continuous Improvement
- Define testing and evaluation methods for AI outputs, workflows, and workflows involving enterprise data
- Improve system quality through prompt tuning, retrieval tuning, workflow redesign, model selection, and structured feedback loops
- Contribute to AI roadmap recommendations from a technical feasibility and maturity perspective
Skills / Profile to Look For
Must-have
- Strong software engineering background
- Experience building AI/LLM-powered applications
- Experience with APIs for OpenAI / Azure OpenAI / Anthropic / Google or similar
- Experience with Python and/or Node.js
- Experience with RAG, vector databases, embeddings, chunking, retrieval strategies
- Experience with orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent)
- Strong knowledge of cloud architecture and secure integrations
- Experience with prompt engineering, evaluation, and AI application debugging
- Ability to design scalable reusable systems
Good to have
- Experience with enterprise SaaS ecosystems such as Salesforce / Oracle / Microsoft
- Experience with agentic workflows
- Experience with observability/evaluation platforms
- Experience working in consulting or product-based delivery organizations
- Exposure to AI governance, data privacy, and model risk considerations
What success looks like in first 6 months
- Establishes the baseline architecture for AI applications
- Builds first reusable accelerator(s)
- Defines engineering standards for GenAI delivery
- Enables fast prototyping with production-minded design
- Acts as technical backbone for roadmap execution
Чем предстоит заниматься
- Design end-to-end AI application architecture for internal and client-facing use cases
- Define patterns for prompt orchestration, agent workflows, retrieval-augmented generation (RAG), tool calling, and enterprise integrations
- Select appropriate models, frameworks, vector stores, and deployment patterns based on cost, performance, and security considerations
- Establish reusable design patterns for future AI accelerators and company-owned IP
- Build production-grade AI applications, copilots, assistants, and workflow automations
- Lead development of reusable AI components that can be scaled across multiple engagements
- Translate roadmap initiatives into technical implementation plans, milestones, and deliverables
- Partner with product and business stakeholders to refine use cases into buildable solutions
- Evaluate and implement commercial LLMs through APIs and enterprise tooling
- Develop robust prompt strategies, context handling logic, tool usage patterns, and fallback mechanisms
- Design and optimize RAG pipelines using structured and unstructured enterprise knowledge sources
- Improve output quality, reliability, and usability of AI applications through testing and iteration
- Define coding standards, deployment standards, logging, monitoring, guardrails, and evaluation practices for AI applications
- Implement mechanisms for observability, tracing, prompt versioning, and response quality review
- Ensure solutions are secure, maintainable, scalable, and aligned with enterprise architecture principles
- Guide non-functional requirements including latency, reliability, token usage, and cost optimization
- Serve as the technical lead for AI engineering efforts
- Mentor and guide the AI Developer / GenAI Engineer
- Support technical decision-making, effort estimation, and feasibility assessments
- Collaborate with cross-functional teams including product, architecture, delivery, QA, and operations
- Participate in discovery sessions with business and delivery teams to identify opportunities for AI enablement
- Work with consulting, sales, and solution engineering teams to understand repeatable use cases
- Support demos, pilots, proofs of concept, and internal enablement where required
- Define testing and evaluation methods for AI outputs, workflows, and workflows involving enterprise data
- Improve system quality through prompt tuning, retrieval tuning, workflow redesign, model selection, and structured feedback loops
- Contribute to AI roadmap recommendations from a technical feasibility and maturity perspective
Что требуется
- Strong software engineering background
- Experience building AI/LLM-powered applications
- Experience with APIs for OpenAI / Azure OpenAI / Anthropic / Google or similar
- Experience with Python and/or Node.js
- Experience with RAG, vector databases, embeddings, chunking, retrieval strategies
- Experience with orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent)
- Strong knowledge of cloud architecture and secure integrations
- Experience with prompt engineering, evaluation, and AI application debugging
- Ability to design scalable reusable systems
- Preferred: Experience with enterprise SaaS ecosystems such as Salesforce / Oracle / Microsoft
- Preferred: Experience with agentic workflows
- Preferred: Experience with observability/evaluation platforms
- Preferred: Experience working in consulting or product-based delivery organizations
- Preferred: Exposure to AI governance, data privacy, and model risk considerations
Преимущества
- Flexible work-life balance
- Traditional benefits
Apex IT is a global consulting firm that provides award-winning services to transform the customer, employee, and student experiences. Since 1997, Apex IT our Salesforce and Oracle experts have provided a full range of enterprise solutions including CRM and related applications that support sales, marketing, and service; financial reporting; HR; and Business Intelligence.
🇺🇸 Соединенные ШтатыConsultingСредняя
Что говорят о компании
3.1/ 5
Зарплата не указана