Title: Senior AI Application Engineer
Location: Navitas Partners Office (4th Floor, Corner Heights, Kalali Road, near DPS School, Vadodara)
Duration: 12 months + Extension
About the Role
Our client is seeking a Senior AI Applications Engineer to join our internal team to build, deploy, and support secure, production-ready AI and automation applications.
This is a senior, hands-on engineering role spanning application development, data integration, generative and agentic AI, cloud deployment, testing, monitoring, and production support.
The ideal candidate combines strong software and data engineering skills with practical experience developing retrieval-augmented generation, intelligent document processing, agentic applications, and enterprise workflow automation.
This is not a research-focused data science or primarily advisory architecture role. The successful candidate must be able to write production-quality code, integrate enterprise systems, deploy secure cloud applications, troubleshoot failures, and continuously improve performance.
Key Responsibilities
- Design, build, test, deploy, and maintain secure, production-grade AI and automation applications.
- Develop generative AI, RAG, semantic search, intelligent document processing, structured extraction, and workflow-automation solutions.
- Build agentic applications that retrieve information, invoke approved tools and APIs, maintain workflow state, manage exceptions, and incorporate human approvals.
- Implement prompt orchestration, tool calling, guardrails, confidence thresholds, retry logic, fallback procedures, and audit trails.
- Develop APIs, connectors, data pipelines, transformations, and integration services for structured and unstructured enterprise data.
- Prepare documents, metadata, embeddings, indexes, and knowledge sources for retrieval-based applications.
- Integrate applications with enterprise platforms using APIs, webhooks, databases, message queues, and event-driven architectures.
- Deploy applications using containers, serverless services, managed cloud platforms, and CI/CD pipelines.
- Develop automated testing and evaluation methods for accuracy, groundedness, retrieval quality, reliability, latency, security, and cost.
- Implement application-level security controls, including authentication, authorization, encryption, secrets management, validation, logging, and least-privilege access.
- Monitor production applications for availability, response quality, model or prompt degradation, data drift, retrieval failures, cost, and integration issues.
- Diagnose and resolve incidents involving application code, APIs, data pipelines, models, prompts, cloud services, permissions, and source systems.
- Tune prompts, retrieval strategies, workflows, thresholds, and application logic based on measured performance and user feedback.
- Participate in client discovery and technical-design sessions, providing engineering input on feasibility, data readiness, integration complexity, effort, and risk.
- Produce technical specifications, code documentation, data mappings, runbooks, release notes, and knowledge-transfer materials.
- Conduct code reviews and help develop reusable components, engineering standards, deployment patterns, and AI accelerators.
Required Qualifications:
- Bachelor's degree in computer science, engineering, information systems, data science, or a related field, or equivalent professional experience.
- Seven or more years of experience in software engineering, application development, data engineering, AI engineering, or a related discipline.
- Three or more years of hands-on experience developing generative AI, intelligent automation, machine-learning, or AI-enabled applications.
- Demonstrated experience moving AI or intelligent automation applications from prototype into production.
- Advanced Python proficiency and strong knowledge of modern software-engineering practices.
- Strong experience with SQL, APIs, data pipelines, data transformation, validation, and structured and unstructured data processing.
- Hands-on experience with large language models, prompt engineering, RAG, embeddings, vector search, semantic retrieval, or document processing.
- Experience building agentic or tool-enabled applications involving orchestration, state management, human approvals, exception handling, or enterprise integrations.
- Experience with LangChain, LangGraph, Semantic Kernel, LlamaIndex, or a comparable framework.
- Production experience with at least one major cloud platform and its AI, application, data, or integration services.
- Experience with Git, automated testing, CI/CD, containers, observability, cloud deployment, and production troubleshooting.
- Working knowledge of application security, identity and access management, data privacy, secrets management, and responsible AI controls.
- Strong analytical, communication, documentation, and problem-solving skills.
Preferred Qualifications:
- Experience supporting applications in a second major cloud environment.
- Experience with Azure OpenAI or Microsoft Foundry, Amazon Bedrock, Google Vertex AI, or a comparable managed AI platform.
- Experience with Power Automate, Logic Apps, Copilot Studio, UiPath, or a comparable automation platform.
- Experience with Azure AI Search, pgvector, Pinecone, Weaviate, OpenSearch, Milvus, or a comparable vector technology.
- Experience with LLM evaluation, AI observability, prompt monitoring, and application-performance testing.
- Experience building intelligent intake, document-processing, customer-service, procurement, quoting, renewal, or sales-operations solutions.
- Experience working in consulting, regulated industries, or client-delivery environments.
- Familiarity with OWASP guidance for web, API, and LLM applications, responsible AI frameworks, or the NIST AI Risk Management Framework.
- Relevant cloud, software-engineering, data, AI, automation, or security certifications.
Success in This Role:
The successful candidate will move AI solutions beyond demonstrations and into secure, stable production use. They will deliver maintainable applications that improve efficiency, reduce errors and cycle time, meet defined performance and security standards, and create reusable engineering practices that strengthen future engagements