Note: Need someone who can come to office bi-weekly.
Role Overview
The Senior AI Engineer designs, builds, and supports secure, reliable AI-enabled applications and backend services for firmwide products and workflows. The role combines strong software engineering with practical experience in enterprise search, retrieval, language models, and cloud AI platforms. The engineer works across product, application, data, security, and business teams to move solutions from technical design through production adoption.
Key Responsibilities Include
- Design, build, and maintain backend services, APIs, and application features for firmwide products and AI-enabled workflows.
- Develop AI application capabilities such as enterprise search, summarization, information extraction, document generation, and conversational experiences using large and small language models.
- Design and integrate secure connections among applications, AI services, enterprise data, and business systems through well-defined APIs, identity controls, and access policies.
- Build retrieval solutions that make relevant enterprise information available to AI applications, including content ingestion, metadata processing, embeddings, indexing, and vector, semantic, or hybrid search.
- Apply sound software engineering practices, including modular design, code review, automated testing, CI/CD, observability, error handling, and performance tuning.
- Evaluate AI features for quality, groundedness, reliability, security, latency, and cost; use evaluation results and user feedback to improve them over time.
- Partner with product, application, data, security, and business teams to translate needs into technical designs and explain implementation choices and trade-offs.
- Own solutions through design, development, deployment, and production support; contribute to technical standards and help other engineers grow.
Preferred Skills and Experience
- Experience with REST APIs, distributed systems, cloud applications, databases, and integration with internal or third-party services.
- Experience delivering applications that use generative AI or LLMs; familiarity with retrieval-augmented generation (RAG), structured outputs, prompt design, and tool or API calling.
- Experience with Microsoft Agent Framework or a comparable agent framework, and with designing AI-based applications, web experiences, chat interfaces, dashboards, or internal business platforms.
- Familiarity with Azure AI Foundry, Azure OpenAI, and Azure cloud services; experience with AWS Bedrock, Google Vertex AI, or comparable platforms is also useful.
- Experience with Elasticsearch and/or Azure AI Search, embeddings, vector search, semantic and hybrid retrieval, and the indexing and evaluation of enterprise content.
- Knowledge of LLM and SLM capabilities, model selection, inference, and application patterns; experience using enterprise platforms such as ChatGPT Enterprise is preferred.
- Familiarity with production monitoring, automated evaluation, application security, data privacy, and responsible AI practices.
Qualifications
- Bachelor’s degree in computer science, engineering, information systems, artificial intelligence, or a related field, or equivalent practical experience.
- 10+ years of professional software engineering or related experience, including substantial work on backend services, APIs, applications, or distributed systems.
- At least 2 years of experience building or integrating generative AI or LLM-based solutions in applications or business systems.
- Demonstrated ability to design and integrate APIs and services and deliver software from development through deployment and production support.
- Experience with automated testing, CI/CD, cloud deployment, logging, monitoring, and troubleshooting production applications.
- Understanding of secure software development, data privacy, and responsible use of AI, with the ability to communicate technical decisions clearly to technical and non-technical colleagues.
Technology Environment
C#/.NET, Python, REST APIs, Azure cloud, Azure AI Foundry, Azure OpenAI, ChatGPT Enterprise, Microsoft Agent Framework or similar, Elasticsearch, embeddings, vector and semantic search, retrieval-augmented generation, large and small language models, CI/CD, automated evaluation, monitoring, and production observability.